© 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. 151199
    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
     service
    -0.26
     mis
    -0.26
     bast
    -0.25
    ä½ķåĨµ
    -0.25
     outsiders
    -0.25
    ser
    -0.24
    sert
    -0.24
    velt
    -0.24
     ser
    -0.24
    [:-
    -0.24
    POSITIVE LOGITS
    ç»ĵæŀĦæĢ§
    0.24
     getP
    0.24
    bare
    0.24
     levy
    0.24
    顺åĪ©å®ĮæĪIJ
    0.24
    finish
    0.23
    æĪIJåĬŁ
    0.23
     Coin
    0.23
    çĶŁèĤ²
    0.23
    ç«ŀæĬĢ
    0.23
    Activations Density 0.333%

    No Known Activations

    This feature has no known activations.