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. 45877
    Prev
    Next
    INDEX
    Explanations

    nosocomial infections

    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
    纳
    -0.28
    ç´į
    -0.26
    ège
    -0.26
    Nonnull
    -0.26
     LIC
    -0.25
    .feature
    -0.25
    建çŃijå¸Ī
    -0.25
     molecular
    -0.25
    çīĮ
    -0.25
    çĬ¶
    -0.25
    POSITIVE LOGITS
    asion
    0.29
    失è°ĥ
    0.28
    çİ·
    0.27
    æĬ¼
    0.26
    unlikely
    0.26
    rin
    0.25
    _attach
    0.25
    rouw
    0.24
    Ñģлож
    0.24
    avan
    0.24
    Activations Density 0.018%

    No Known Activations