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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 7-TRANSCODER-HP
    4. 1392
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sey
    -0.26
    ìĭł
    -0.25
    ìĹ´
    -0.25
     xu
    -0.25
     basic
    -0.25
     tether
    -0.25
    lé
    -0.24
     :
    -0.24
    TZ
    -0.24
     ép
    -0.24
    POSITIVE LOGITS
    isoft
    0.28
    å·´æĸ¯
    0.26
    =*
    0.26
    -sensitive
    0.25
    åį´æĺ¯
    0.24
    ç¡IJ
    0.24
    ****************************************************************************
    0.23
    çIJĨä¼ļ
    0.23
    -taking
    0.23
    -pencil
    0.23
    Activations Density 0.003%

    No Known Activations