© 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. 107997
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
    éĹ´æİ¥
    -0.27
    elho
    -0.27
    ä¸ŃåĽ½çī¹èī²
    -0.26
     khấu
    -0.26
     {?}
    -0.25
    IDA
    -0.25
    æĸ°é²ľ
    -0.25
    MSN
    -0.25
     gracefully
    -0.25
    ductory
    -0.24
    POSITIVE LOGITS
    ç´§åĩij
    0.39
     rapid
    0.38
    çĸ²åĬ³
    0.37
    åħ¨å¤©
    0.36
    è¿ŀç»Ń
    0.36
    æĹ¥å¤ľ
    0.35
    å¿Ļç¢Į
    0.34
     intensive
    0.34
     continuous
    0.34
    å¿«
    0.34
    Activations Density 50.770%

    No Known Activations