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. 1750
    Prev
    Next
    INDEX
    Explanations

    Names and name fragments

    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
    pare
    -0.29
    åĪĽç«ĭ
    -0.28
    parent
    -0.28
    imes
    -0.27
    å¤įåIJĪ
    -0.26
    ions
    -0.26
    临åºĬ
    -0.26
    ä¼ĺ
    -0.26
    OTS
    -0.26
    éŨ
    -0.25
    POSITIVE LOGITS
    ynes
    0.29
    achusetts
    0.26
    omi
    0.26
    [*
    0.25
     Seam
    0.25
    ystack
    0.25
    resizing
    0.25
    oval
    0.25
    connexion
    0.25
    大éĺŁ
    0.25
    Activations Density 0.002%

    No Known Activations