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. 46461
    Prev
    Next
    INDEX
    Explanations

    Excitement/bonus

    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
    éĺħ读åħ¨æĸĩ
    -0.29
    æĢĿ
    -0.28
    avail
    -0.25
    orks
    -0.25
    åħ³äºİæĪij们
    -0.25
     catalogs
    -0.24
    alse
    -0.24
     engine
    -0.24
    åľ¨è¿Ļ
    -0.24
    igs
    -0.24
    POSITIVE LOGITS
    èĬĤ
    0.29
    tingham
    0.25
    ointed
    0.25
    æı¡ä½ı
    0.24
    寿åij½
    0.23
    elps
    0.23
    recipient
    0.23
    ÑĢеÑģ
    0.23
    éķ¿çĽ¸
    0.23
    SENT
    0.23
    Activations Density 0.006%

    No Known Activations