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. 6962
    Prev
    Next
    INDEX
    Explanations

    /

    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
     see
    -0.08
    .fil
    -0.07
    培训
    -0.07
    �
    -0.07
    きっと
    -0.07
    fcc
    -0.07
    ian
    -0.07
    휙
    -0.07
    ,in
    -0.07
    條
    -0.07
    POSITIVE LOGITS
     counterpart
    0.08
    bservable
    0.08
     Surprise
    0.08
     cleansing
    0.07
    电子产品
    0.07
     Entities
    0.07
     Southampton
    0.07
     Sale
    0.07
    特斯拉
    0.07
     הדבר
    0.07
    Activations Density 0.008%

    No Known Activations