© 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. 20-TRANSCODER-HP
    7. 108687
    Prev
    Next
    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¤ĸè´¸
    -0.26
     Ñģвоими
    -0.26
    女åŃ©åŃIJ
    -0.25
    设ç«ĭ
    -0.25
    Router
    -0.25
    çįĴ
    -0.25
    orget
    -0.24
     watch
    -0.24
     impact
    -0.24
    ¯¯
    -0.24
    POSITIVE LOGITS
    optic
    0.29
     chap
    0.27
    achable
    0.27
    parity
    0.25
    æ³IJ
    0.24
    ÑĪа
    0.24
    ausible
    0.24
    down
    0.24
    mented
    0.24
    enstein
    0.24
    Activations Density 9.794%

    No Known Activations