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. 3979
    Prev
    Next
    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash

    mentions of “module” or “modules,” especially in technical or code-related contexts.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    æ³ķæ²»
    -0.28
    ↵↵↵
    -0.26
    iform
    -0.25
     den
    -0.24
    æĽ´é«ĺ
    -0.24
     coer
    -0.23
    oses
    -0.23
     Brooke
    -0.23
    å®ŀ践活åĬ¨
    -0.23
    isme
    -0.23
    POSITIVE LOGITS
    lags
    0.29
     Bá
    0.26
    omens
    0.26
    rence
    0.25
    åĢº
    0.25
    amation
    0.25
    è´
    0.25
     preca
    0.24
     Tech
    0.24
    åį°è±¡æ·±åĪ»
    0.24
    Activations Density 0.009%

    No Known Activations