© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53567
    Prev
    Next
    INDEX
    Explanations

    relay competitions and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ening
    -0.11
    ater
    -0.09
    ⨯
    -0.09
    yal
    -0.09
    èĨĽ
    -0.08
    åĥļ
    -0.08
    DL
    -0.08
    ifax
    -0.08
    é«ĺåİŁ
    -0.08
    yc
    -0.08
    POSITIVE LOGITS
    edin
    0.10
    ues
    0.10
     dụ
    0.10
    ìĤ¬ìĿ´
    0.10
    è¿ĩæĿ¥
    0.09
    buster
    0.09
    ä¸įéĢļ
    0.09
    å¼ĢæĿ¥
    0.09
    erre
    0.09
    èIJ½ãģ¡
    0.09
    Activations Density 0.016%

    No Known Activations