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. 7-TRANSCODER-HP
    4. 327
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abled
    -0.30
    éĤ£æĺ¯
    -0.27
    actics
    -0.26
    好人
    -0.26
    heard
    -0.26
    trand
    -0.25
    åͱ
    -0.25
    åĽŀé¦ĸ
    -0.25
    historic
    -0.25
    èĭ±éĽĦ
    -0.24
    POSITIVE LOGITS
     createTime
    0.27
    око
    0.27
    çļĦæľĢ大
    0.25
    ör
    0.24
    enie
    0.24
     SQ
    0.24
    åĬ±
    0.24
     elim
    0.24
     MGM
    0.23
    meg
    0.23
    Activations Density 0.004%

    No Known Activations