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. 88924
    Prev
    Next
    INDEX
    Explanations

    many

    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
    签订
    -0.07
     제공
    -0.07
    族自治
    -0.07
    .filter
    -0.07
     England
    -0.07
    /m
    -0.07
    真实
    -0.06
    terror
    -0.06
    pure
    -0.06
    月薪
    -0.06
    POSITIVE LOGITS
    发展机遇
    0.07
     обязательно
    0.07
     datingsider
    0.07
     wcześniej
    0.07
    думал
    0.06
    下行
    0.06
     birthdays
    0.06
    民企
    0.06
     oczywiście
    0.06
     about
    0.06
    Activations Density 0.014%

    No Known Activations