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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 111282
    Prev
    Next
    INDEX
    Explanations

    speed/signal

    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_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
    aporation
    -0.07
    �
    -0.07
     vul
    -0.07
    兮
    -0.07
    *(-
    -0.06
    <_
    -0.06
    "',↵
    -0.06
     affid
    -0.06
    _flow
    -0.06
     fro
    -0.06
    POSITIVE LOGITS
    �
    0.08
     Vancouver
    0.07
     tuning
    0.07
    �
    0.07
    许多人
    0.07
    ערכת
    0.07
     ajust
    0.07
    有机会
    0.07
     müşteri
    0.07
     nivel
    0.07
    Activations Density 0.021%

    No Known Activations