© 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. 24-TRANSCODER-HP
    7. 149158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éģĵ
    -0.30
    gram
    -0.28
    åı·
    -0.26
    irit
    -0.25
    orders
    -0.25
     Gram
    -0.25
    inci
    -0.24
    æľīå¾ħ
    -0.24
    è¶³å¤ŁçļĦ
    -0.24
    订
    -0.24
    POSITIVE LOGITS
    çĭĢ
    0.28
    RELEASE
    0.28
    suppress
    0.26
    æĶ¾å¤§
    0.26
     confess
    0.26
     RELEASE
    0.24
    aeda
    0.24
    ampler
    0.24
    /cc
    0.24
     lov
    0.24
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.