© 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. 23-TRANSCODER-HP
    7. 25497
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Composition
    -0.30
     compose
    -0.27
    /sources
    -0.26
    æĺ¯ä¸Ģ座
    -0.25
    reff
    -0.25
     Suff
    -0.25
    "indices
    -0.25
    holders
    -0.24
     Dome
    -0.24
    èĭ¦èĭ¦
    -0.24
    POSITIVE LOGITS
    çŁ¥
    0.32
    ieux
    0.29
     rather
    0.29
    oss
    0.29
    èĢĮä¸įæĺ¯
    0.28
     instead
    0.27
     plutôt
    0.27
     analog
    0.27
     sab
    0.26
    ch
    0.26
    Activations Density 0.005%

    No Known Activations