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. 72126
    Prev
    Next
    INDEX
    Explanations

    say "DIS word"

    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
    ึง
    -0.07
    Promise
    -0.07
    暾
    -0.06
     invitation
    -0.06
    שמת
    -0.06
    itous
    -0.06
     prospective
    -0.06
     ámbito
    -0.06
    clado
    -0.06
     posed
    -0.06
    POSITIVE LOGITS
    .turn
    0.08
    \Form
    0.07
    装扮
    0.07
    蔹
    0.07
    _leaf
    0.07
    .pagination
    0.07
    .sup
    0.07
    .attribute
    0.07
    部副
    0.07
    เศร
    0.07
    Activations Density 0.000%

    No Known Activations