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. 97882
    Prev
    Next
    INDEX
    Explanations

    Jim

    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
     Subject
    -0.26
     clones
    -0.26
    çŃĴ
    -0.26
    _Out
    -0.26
    arith
    -0.25
    weeney
    -0.25
    erea
    -0.25
     Vendor
    -0.25
    owel
    -0.24
    imps
    -0.24
    POSITIVE LOGITS
    ä¸ĩå®¶
    0.31
    atters
    0.27
    ä¼ļ让
    0.25
    айл
    0.25
    ager
    0.24
     finalize
    0.24
    omi
    0.24
    å°±åľ¨
    0.24
     Laur
    0.23
     fier
    0.23
    Activations Density 0.006%

    No Known Activations