© 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. 25621
    Prev
    Next
    INDEX
    Explanations

    from

    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
    assen
    -0.27
    phalt
    -0.27
    nty
    -0.25
    æĦı
    -0.25
    duce
    -0.25
    éĹ®ä»ĸ
    -0.25
    ,List
    -0.24
    enuity
    -0.23
     cannon
    -0.23
    赤
    -0.23
    POSITIVE LOGITS
     tụ
    0.27
    è²Įä¼¼
    0.26
    .summary
    0.24
     Äiju
    0.23
    彧
    0.23
     motto
    0.23
     اÙĦعÙħ
    0.23
    oba
    0.23
     Bei
    0.22
    ê·ľ
    0.22
    Activations Density 0.003%

    No Known Activations