© 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. 30-TRANSCODER-HP
    7. 96291
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¡
    -0.30
    .vo
    -0.26
    away
    -0.26
    ipple
    -0.25
    ä¸īæĿ¡
    -0.24
     XF
    -0.24
    itizen
    -0.24
     preorder
    -0.24
    iÅĤ
    -0.24
    à¸īาย
    -0.24
    POSITIVE LOGITS
     Lama
    0.29
    dar
    0.28
    åĨµ
    0.27
    akh
    0.27
    amat
    0.27
    dess
    0.27
    fore
    0.25
    вал
    0.25
    夯
    0.25
     pragma
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.