© 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. 106887
    Prev
    Next
    INDEX
    Explanations

    code and mixed languages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ī
    -0.33
    ä½ĵçİ°
    -0.28
    emony
    -0.28
     indications
    -0.28
    æīįç®Ĺ
    -0.28
     indicate
    -0.28
     attempted
    -0.28
    çĹķ迹
    -0.28
     observed
    -0.27
    ä¸įåı¯æĢĿè®®
    -0.27
    POSITIVE LOGITS
    æľīåĪ©
    0.31
    使å¾Ĺ
    0.30
    妨ç¢į
    0.30
    venient
    0.29
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.29
    åĬłä¹ĭ
    0.29
    ç¢į
    0.28
     conveniently
    0.28
    è¿Ļå°±
    0.28
    unct
    0.28
    Activations Density 88.116%

    No Known Activations