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. 46437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oks
    -0.29
    cq
    -0.26
     Maps
    -0.26
     ver
    -0.26
    KIT
    -0.25
     Once
    -0.25
     maps
    -0.25
    GORITHM
    -0.24
    que
    -0.24
    amin
    -0.24
    POSITIVE LOGITS
     Jah
    0.28
    brook
    0.26
     дог
    0.26
    instructions
    0.26
     Coord
    0.25
     scrim
    0.25
    rome
    0.25
    laughter
    0.24
    çļĦç¼ĺæķħ
    0.24
     Signing
    0.24
    Activations Density 0.012%

    No Known Activations