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. 88475
    Prev
    Next
    INDEX
    Explanations

    Things

    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
    workspace
    -0.09
     forbidden
    -0.08
    wał
    -0.07
    lij
    -0.07
    ☉
    -0.07
    相应
    -0.07
     Kim
    -0.07
    lock
    -0.07
    precio
    -0.07
    因为他
    -0.07
    POSITIVE LOGITS
     arrog
    0.08
     accomp
    0.07
     الإنس
    0.07
    OUNTRY
    0.07
    ("%
    0.07
    ('&
    0.07
    近百
    0.07
    ancer
    0.06
     prolifer
    0.06
    を行い
    0.06
    Activations Density 0.137%

    No Known Activations