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. 15478
    Prev
    Next
    INDEX
    Explanations

    classroom

    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
     specialties
    -0.29
    ilename
    -0.26
    witter
    -0.26
     conse
    -0.25
    *out
    -0.25
     distinctly
    -0.24
    ixel
    -0.24
    iles
    -0.24
    ä½ĵåŀĭ
    -0.24
    *@
    -0.24
    POSITIVE LOGITS
    declar
    0.29
    ÑĩÑĮ
    0.28
    _|
    0.27
    kea
    0.27
    enÃŃ
    0.26
     Famous
    0.25
    _portal
    0.25
    åłµ
    0.25
    åIJĦåĽ½
    0.25
    æĽ´å¼º
    0.25
    Activations Density 0.000%

    No Known Activations