© 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. 23768
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions/code

    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
    .getClassName
    -0.29
    .apple
    -0.27
    łģ
    -0.27
    TypeError
    -0.27
     stopped
    -0.26
    _bundle
    -0.25
    noon
    -0.24
    coration
    -0.24
    dur
    -0.24
    YLE
    -0.24
    POSITIVE LOGITS
    寡
    0.29
    æIJĶ
    0.27
    Begin
    0.26
    æĥĺ
    0.25
    Handle
    0.25
    oze
    0.25
    èĬ¥
    0.25
    erto
    0.25
     Levine
    0.24
    俶
    0.24
    Activations Density 0.004%

    No Known Activations