© 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. 30-TRANSCODER-HP
    7. 94894
    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
    Negative Logits
     off
    -0.28
    onte
    -0.28
    建çŃijä¸ļ
    -0.26
    unned
    -0.25
    ublished
    -0.25
    éĻĦ
    -0.25
     forever
    -0.25
    aled
    -0.25
     rural
    -0.25
    驳
    -0.24
    POSITIVE LOGITS
    宣
    0.28
    _party
    0.27
     DEFAULT
    0.26
    ä¸īåĪĨä¹ĭä¸Ģ
    0.26
    .trip
    0.26
    çļĦä¸įåIJĮ
    0.25
    âĤ¬“
    0.25
    é©´
    0.25
    $filter
    0.24
    å¯Ĩ
    0.24
    Activations Density 0.903%

    No Known Activations

    This feature has no known activations.