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

    Neuronpedia

    APICircuit 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. 48459
    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
     angles
    -0.07
     MessageType
    -0.07
    .richTextBox
    -0.07
     narc
    -0.07
     vehicles
    -0.07
     ElementType
    -0.07
     damaging
    -0.07
    .mContext
    -0.07
     sprawling
    -0.07
     engagements
    -0.06
    POSITIVE LOGITS
    écial
    0.06
    늣
    0.06
    횔
    0.06
     event
    0.06
    ahir
    0.06
    ają
    0.06
    CI
    0.06
    kses
    0.06
    .Config
    0.06
    pi
    0.06
    Activations Density 0.013%

    No Known Activations