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. 11-TRANSCODER-HP
    4. 54357
    Prev
    Next
    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onym
    -0.27
    .ordinal
    -0.25
    =count
    -0.25
    ä¸įåħĭ
    -0.24
    oble
    -0.24
     oid
    -0.24
    antha
    -0.24
    cid
    -0.24
    计
    -0.23
    æĸ°éĹ»è®°èĢħ
    -0.23
    POSITIVE LOGITS
    éĥ½å¾Ī
    0.29
     setup
    0.26
    Posts
    0.26
    lo
    0.25
     sale
    0.25
    eni
    0.25
     Collections
    0.25
    derived
    0.25
    iii
    0.25
    paragus
    0.24
    Activations Density 0.084%

    No Known Activations