© 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. 25400
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    Negative Logits
    irs
    -0.29
    请éĢīæĭ©
    -0.28
    ités
    -0.25
    ytt
    -0.25
    è¿Ļ个èģĮä¸ļ
    -0.25
    -defined
    -0.24
    RCT
    -0.24
    defined
    -0.24
    åIJİèĢħ
    -0.24
    KO
    -0.24
    POSITIVE LOGITS
    èĦĨ
    0.29
     pest
    0.25
     Bernstein
    0.24
    伯
    0.24
     robe
    0.23
     Ber
    0.23
    leh
    0.23
    ä¸ľæµ·
    0.23
    loud
    0.23
     Inst
    0.23
    Activations Density 0.003%

    No Known Activations