© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129796
    Prev
    Next
    INDEX
    Explanations

    online forum posts

    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
    promotion
    -0.30
    ä¸įå¤Ł
    -0.29
    ä¸į足
    -0.29
     promotion
    -0.28
    unts
    -0.28
    ä¸į足以
    -0.28
     imp
    -0.28
    没æľī
    -0.27
    emes
    -0.27
    ä¸į大
    -0.27
    POSITIVE LOGITS
    转载请
    0.31
    ære
    0.27
    è¯ģæĺİ
    0.26
    rior
    0.26
    æĪijçŁ¥éģĵ
    0.26
     somehow
    0.25
    iquid
    0.25
    æIJŀå®ļ
    0.25
    æĪijèĥ½
    0.24
    å¾ģæĶ¶
    0.24
    Activations Density 70.424%

    No Known Activations