© 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. 35095
    Prev
    Next
    INDEX
    Explanations

    rates

    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
    å¼¼
    -0.09
    åĸŁ
    -0.09
    tit
    -0.09
    its
    -0.08
    çľĭæĿ¥
    -0.08
    è·¨
    -0.08
    ár
    -0.08
     ers
    -0.08
    æ¡¢
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    æĭĨ
    0.09
    udio
    0.09
     rate
    0.09
    åĩ¿
    0.09
     rates
    0.09
    -rate
    0.09
    (rate
    0.09
    ë¦Ń
    0.09
    è·Łä»ĸ
    0.09
    åĩłçİĩ
    0.09
    Activations Density 0.065%

    No Known Activations