© 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. 25257
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    first
    -0.31
     first
    -0.30
    第ä¸Ģ天
    -0.29
    ä»ħæľī
    -0.28
    第ä¸Ģ家
    -0.28
    åĪĿ级
    -0.27
    æŀª
    -0.27
     Early
    -0.27
    æĹ©æľŁ
    -0.27
     early
    -0.26
    POSITIVE LOGITS
    .TXT
    0.30
     multiline
    0.27
    >NN
    0.27
    -rounded
    0.27
    æľĢåIJİä¸Ģ次
    0.26
    ONUS
    0.26
    endet
    0.26
    -Sep
    0.26
    à°³
    0.25
    OwnProperty
    0.25
    Activations Density 0.003%

    No Known Activations