© 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. 25601
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
    éĿł
    -0.30
    arella
    -0.28
    Ñĥп
    -0.25
    åĪĨå¸ĥå¼ı
    -0.25
     luc
    -0.25
    etCode
    -0.24
     gracias
    -0.24
    Catch
    -0.24
    unte
    -0.24
    ess
    -0.24
    POSITIVE LOGITS
     adjustment
    0.37
    åĬłåĢį
    0.37
     adjust
    0.36
    åĩıåħį
    0.34
    åīĬåĩı
    0.34
     Adjust
    0.33
     adjustments
    0.33
     adjusted
    0.32
    éĢĤå½ĵ
    0.32
     Adjustment
    0.32
    Activations Density 0.005%

    No Known Activations