© 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. 12-TRANSCODER-HP
    7. 24108
    Prev
    Next
    INDEX
    Explanations

    confusing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åįķ纯
    -0.28
    设计æĸ¹æ¡Ī
    -0.27
     corr
    -0.27
    èĸ°
    -0.27
     scrap
    -0.27
    ATS
    -0.26
    cars
    -0.26
    é©·
    -0.26
    eric
    -0.26
     real
    -0.26
    POSITIVE LOGITS
    riet
    0.29
     Quarry
    0.26
    CAST
    0.25
    айн
    0.25
    主åĬ¨æĢ§
    0.25
    éķ¿æķĪæľºåĪ¶
    0.25
    ãģį
    0.24
    achu
    0.24
    _FINE
    0.24
    è¿ij
    0.24
    Activations Density 0.005%

    No Known Activations