© 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. 58569
    Prev
    Next
    INDEX
    Explanations

    the

    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
     language
    -0.30
    è¯Ńè¨Ģ
    -0.27
    è¯Ń
    -0.26
    大è¡Ĺ
    -0.26
    by
    -0.25
     emphas
    -0.24
    uv
    -0.24
    AGIC
    -0.24
    Language
    -0.24
    ÅŁehir
    -0.23
    POSITIVE LOGITS
    夯
    0.26
    ymology
    0.26
    oload
    0.26
     Cler
    0.26
    串
    0.26
    pad
    0.24
    PAD
    0.24
    itez
    0.24
    ä¹ĭ称
    0.23
    _calls
    0.23
    Activations Density 0.004%

    No Known Activations