© 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. 23639
    Prev
    Next
    INDEX
    Explanations

    when

    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
    _Begin
    -0.26
    温馨æıIJ示
    -0.26
    èĽĽ
    -0.25
     leds
    -0.25
    åı¯æĥ³
    -0.25
    lient
    -0.25
     canv
    -0.25
     vezes
    -0.24
    å½ĵåį³
    -0.23
     szczeg
    -0.23
    POSITIVE LOGITS
    å°ĨæĿ¥
    0.35
     future
    0.33
    ä»ĬåIJİ
    0.32
     Eventually
    0.31
    æľªæĿ¥çļĦ
    0.31
    æĺİå¹´
    0.31
     someday
    0.30
    åľ¨æľªæĿ¥
    0.28
    æľªæĿ¥
    0.28
    åĪ°æŶåĢĻ
    0.28
    Activations Density 0.008%

    No Known Activations