© 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. 23770
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
    Not in Any Lists

    No Comments

    Negative Logits
     deaths
    -0.28
     Deaths
    -0.28
    è¿Ī
    -0.27
     mappings
    -0.26
    jes
    -0.26
    åı®
    -0.26
    elen
    -0.25
    éĩį大
    -0.25
    mis
    -0.25
     pes
    -0.24
    POSITIVE LOGITS
    ç»ħ
    0.30
    è¨Ī
    0.28
    /count
    0.27
    计
    0.27
    èIJ
    0.26
    ĥģ
    0.26
    ochen
    0.26
    樯
    0.24
    为äºĨéģ¿åħį
    0.24
     approached
    0.24
    Activations Density 0.003%

    No Known Activations