© 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. 25-TRANSCODER-HP
    7. 109447
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    好åIJ§
    -0.27
    æĬĬè¿ĻäºĽ
    -0.27
     Again
    -0.27
     kad
    -0.27
    è¡·
    -0.26
    ONES
    -0.25
    Again
    -0.25
     guys
    -0.24
     again
    -0.24
    .mag
    -0.24
    POSITIVE LOGITS
     tear
    0.25
    mı
    0.25
    ä¸īå±Ĥ
    0.25
    elle
    0.25
    rase
    0.24
     hyper
    0.24
     ëıĮìķĦ
    0.24
    ast
    0.24
     rode
    0.23
    没æľīä»»ä½ķ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.