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. 146337
    Prev
    Next
    INDEX
    Explanations

    sections and portions

    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
    åĪĩãĤĬ
    -0.29
     compatible
    -0.28
     uniformly
    -0.26
     class
    -0.25
     uniform
    -0.25
    st
    -0.25
     rock
    -0.24
    èįĶæŀĿ
    -0.24
    ass
    -0.24
    vas
    -0.24
    POSITIVE LOGITS
    msgid
    0.28
    ibbon
    0.28
    orgh
    0.27
    ouro
    0.27
    cue
    0.27
    orf
    0.27
    agnar
    0.26
    :maj
    0.26
    omore
    0.26
    atoire
    0.26
    Activations Density 0.122%

    No Known Activations