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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 59575
    Prev
    Next
    INDEX
    Explanations

    code

    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
     women
    -0.08
    aped
    -0.07
    钇
    -0.07
     navigating
    -0.06
    matchCondition
    -0.06
    颗
    -0.06
    收到
    -0.06
    Look
    -0.06
     notch
    -0.06
    Nu
    -0.06
    POSITIVE LOGITS
    (actual
    0.07
     rek
    0.07
    博览会
    0.07
    .region
    0.06
    儘
    0.06
    -eslint
    0.06
    -sided
    0.06
    .Default
    0.06
    .ru
    0.06
    ornecedor
    0.06
    Activations Density 0.005%

    No Known Activations