© 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. 27-TRANSCODER-HP
    7. 58416
    Prev
    Next
    INDEX
    Explanations

    God

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    注
    -0.28
     Words
    -0.26
    esen
    -0.26
    å¹³åĿ¦
    -0.25
    æķ²
    -0.25
    æĨ¬
    -0.24
    -indent
    -0.24
    antis
    -0.24
    ivent
    -0.23
    åľºåIJĪ
    -0.23
    POSITIVE LOGITS
    帮åĬ©
    0.33
    帮ä»ĸ
    0.31
     help
    0.31
    帮å¿Ļ
    0.31
     tell
    0.30
    Help
    0.29
    help
    0.29
    æħ¢æħ¢åľ°
    0.29
    幫åĬ©
    0.28
    tex
    0.27
    Activations Density 0.005%

    No Known Activations