© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89227
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡Įç¨ĭ
    -0.29
    éĩijåŃĹå¡Ķ
    -0.28
    åºı
    -0.28
    maf
    -0.27
     figure
    -0.26
    éĵŃ
    -0.25
     trip
    -0.25
     purse
    -0.24
     ped
    -0.24
    ủ
    -0.24
    POSITIVE LOGITS
     synd
    0.28
    ervention
    0.27
     Laur
    0.26
    elter
    0.26
    Meanwhile
    0.26
    ä¿Ŀå®Ī
    0.25
    hoff
    0.25
    æļĸæ°Ķ
    0.25
    elters
    0.25
    åħ¥é©»
    0.25
    Activations Density 12.561%

    No Known Activations