Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 7301
    Prev
    Next
    INDEX
    Explanations

    smirks and grins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lecturer
    -0.08
    AutoSize
    -0.07
     Aurora
    -0.07
    生动
    -0.07
    的内容
    -0.07
    使者
    -0.07
     Anth
    -0.07
    棹
    -0.07
    :The
    -0.07
    lok
    -0.06
    POSITIVE LOGITS
    _MESSAGES
    0.08
    白马
    0.07
     vin
    0.07
     contracts
    0.07
     recession
    0.07
    (;
    0.07
    withdraw
    0.06
    $L
    0.06
    Ids
    0.06
    fp
    0.06
    Activations Density 0.017%

    No Known Activations