© 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. 129820
    Prev
    Next
    INDEX
    Explanations

    was

    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
    awning
    -0.28
     crown
    -0.26
    æľĭ
    -0.25
     jednoczeÅĽnie
    -0.25
    .slim
    -0.25
     Crown
    -0.25
     Disclaimer
    -0.25
    awns
    -0.24
    æľįåĬ¡è´¨éĩı
    -0.24
    å©ī
    -0.24
    POSITIVE LOGITS
    è¾¹ä¸Ĭ
    0.30
    她说
    0.28
    etration
    0.27
     EÄŁ
    0.27
    ød
    0.26
    讼
    0.26
     revealed
    0.25
     taxed
    0.25
    èĢģå®ŀ
    0.24
    roph
    0.24
    Activations Density 6.507%

    No Known Activations