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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 9817
    Prev
    Next
    INDEX
    Explanations

    rector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ul
    -0.07
     Narrow
    -0.06
     scratching
    -0.06
     Cavaliers
    -0.06
    .idx
    -0.06
    issippi
    -0.06
    Pros
    -0.06
    ’am
    -0.06
     timelines
    -0.06
    Push
    -0.06
    POSITIVE LOGITS
    百分
    0.08
    dfa
    0.07
    酦
    0.07
     Junction
    0.07
    _arguments
    0.06
    全体
    0.06
    一起去
    0.06
     these
    0.06
     Princeton
    0.06
    _unsigned
    0.06
    Activations Density 0.002%

    No Known Activations