© 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. 56576
    Prev
    Next
    INDEX
    Explanations

    ap

    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
     Bel
    -0.29
    ottie
    -0.25
    褶
    -0.25
    ally
    -0.25
    æ½®
    -0.24
     Bot
    -0.24
     Again
    -0.24
    Bel
    -0.24
    ef
    -0.24
    de
    -0.24
    POSITIVE LOGITS
    cum
    0.27
    天æīį
    0.25
     Discipline
    0.25
     excavation
    0.25
    æĿ¥æºIJ
    0.24
     excav
    0.24
    reten
    0.23
    åĸĻ
    0.23
     antagonist
    0.23
     ÙĪجÙĩ
    0.23
    Activations Density 0.000%

    No Known Activations