© 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. 149132
    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
     integral
    -0.27
     closer
    -0.26
    ä½ľèĢħæīĢæľī
    -0.25
    èįı
    -0.24
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.24
    ingroup
    -0.24
    shal
    -0.24
    亲åĪĩ
    -0.24
    åIJ»
    -0.23
    adata
    -0.23
    POSITIVE LOGITS
    uss
    0.27
    leet
    0.25
    unsafe
    0.24
    axed
    0.24
    usted
    0.23
    fine
    0.23
    .nz
    0.23
    该æ¡Ī
    0.23
    åĵij
    0.23
    æľĢ好
    0.23
    Activations Density 4.543%

    No Known Activations

    This feature has no known activations.