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. 48386
    Prev
    Next
    INDEX
    Explanations

    name

    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
    を見せ
    -0.07
     Oscar
    -0.07
     offering
    -0.07
    _threshold
    -0.06
     אור
    -0.06
    trer
    -0.06
    צ
    -0.06
     GtkWidget
    -0.06
     Psr
    -0.06
     vol
    -0.06
    POSITIVE LOGITS
     recher
    0.08
    _dispatcher
    0.07
    Refs
    0.07
    _DU
    0.07
    _thumbnail
    0.07
     webhook
    0.06
    :image
    0.06
     sách
    0.06
    :no
    0.06
    /Application
    0.06
    Activations Density 0.028%

    No Known Activations