© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 51062
    Prev
    Next
    INDEX
    Explanations

    hacking

    np_max-act · gemini-2.0-flash

    mentions of hacking and unauthorized digital intrusions into computer systems, databases, or networks (i.e., cybercrime activity).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    现存
    -0.07
    可以帮助
    -0.07
     Howell
    -0.07
    下面是
    -0.07
     "{\"
    -0.07
     SES
    -0.07
     Inputs
    -0.07
     physician
    -0.07
    صرف
    -0.07
    톹
    -0.07
    POSITIVE LOGITS
     Sector
    0.07
    faf
    0.07
    jal
    0.07
    (team
    0.06
    そ
    0.06
    _categorical
    0.06
     pratic
    0.06
     remodel
    0.06
     oficial
    0.06
    _FACTORY
    0.06
    Activations Density 0.040%

    No Known Activations