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. 54554
    Prev
    Next
    INDEX
    Explanations

    Twitter

    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
    quality
    -0.28
     lot
    -0.28
    jax
    -0.27
     LOT
    -0.27
    imits
    -0.27
    èĭ±æł¼
    -0.26
    jective
    -0.26
    lace
    -0.25
    åѦçĶŁçļĦ
    -0.25
    locking
    -0.25
    POSITIVE LOGITS
    ori
    0.27
    бÑĢа
    0.27
    oui
    0.25
     ÑģовеÑĢÑĪен
    0.25
    offs
    0.25
    åij¼åĴĮ
    0.25
    ktop
    0.24
    $"
    0.24
     @[
    0.24
    amac
    0.24
    Activations Density 0.174%

    No Known Activations