© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108504
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urring
    -0.29
    ivec
    -0.27
    nop
    -0.27
    ']>
    -0.26
    ldb
    -0.26
    rir
    -0.26
    _Resource
    -0.25
    sched
    -0.25
    mgr
    -0.25
    izin
    -0.25
    POSITIVE LOGITS
     retract
    0.28
     especÃŃfico
    0.27
    举ä¾ĭ
    0.27
    haft
    0.26
    楫
    0.26
    åİŁæĿ¥æĺ¯
    0.26
    æĿĸ
    0.25
    身é«ĺ
    0.25
    heels
    0.25
    羣çļ®
    0.25
    Activations Density 5.319%

    No Known Activations

    This feature has no known activations.