© 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. 131037
    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
    Negative Logits
    è¿°
    -0.28
     av
    -0.28
     joys
    -0.27
    udeau
    -0.27
    EntryPoint
    -0.26
    ader
    -0.26
    reatest
    -0.23
    ADER
    -0.23
     bare
    -0.23
     womb
    -0.23
    POSITIVE LOGITS
    phis
    0.29
    [ID
    0.26
    aul
    0.26
    (Clone
    0.26
    ãģĸ
    0.26
    phrase
    0.25
    awe
    0.24
    èĬ
    0.24
    (SP
    0.24
    yne
    0.24
    Activations Density 8.497%

    No Known Activations

    This feature has no known activations.