© 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. 24-TRANSCODER-HP
    7. 149153
    Prev
    Next
    INDEX
    Explanations

    server

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    emean
    -0.36
    riangle
    -0.31
    emin
    -0.29
    YRO
    -0.28
    emax
    -0.28
    ursal
    -0.27
    æµĵ缩
    -0.27
    ertino
    -0.27
    urname
    -0.26
    emi
    -0.26
    POSITIVE LOGITS
    wise
    0.27
    ãģªãĤĭ
    0.26
    ly
    0.26
    è¿İ
    0.26
    Impl
    0.25
    wiki
    0.25
    -bound
    0.25
     wh
    0.25
     hosting
    0.25
    d
    0.25
    Activations Density 1.551%

    No Known Activations