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. 54266
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    å±Ĥ次
    -0.28
     Incre
    -0.26
    æ²Ī
    -0.26
    æľ¬è½®
    -0.26
    鱿
    -0.25
    yü
    -0.25
    quisition
    -0.25
    å§¥
    -0.24
    äºļ马
    -0.24
    .Entry
    -0.24
    POSITIVE LOGITS
    gles
    0.29
     Boeh
    0.28
    jing
    0.25
    culture
    0.25
    UPS
    0.24
    æĹģ
    0.23
    gpu
    0.23
     wur
    0.23
    Bes
    0.23
    ABI
    0.23
    Activations Density 0.013%

    No Known Activations