© 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. 53809
    Prev
    Next
    INDEX
    Explanations

    know why, reason, recognize, see if

    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
    è§īå¾Ĺå¾Ī
    -0.09
    çļĦæĥ³æ³ķ
    -0.09
    ç§ģä¸ĭ
    -0.09
    é³ı
    -0.09
    妻åŃIJ
    -0.09
    ä¸ĢéĹ´
    -0.09
    éļIJå½¢
    -0.09
    TTY
    -0.09
     unlink
    -0.09
    建çŃijéĿ¢ç§¯
    -0.09
    POSITIVE LOGITS
    _kw
    0.09
    _paragraph
    0.08
    entes
    0.08
     Pole
    0.08
    ãģĻãģİãģ¦
    0.08
    -question
    0.08
    reon
    0.07
    é«ĺå°ļ
    0.07
    æĿĨ
    0.07
     sure
    0.07
    Activations Density 0.161%

    No Known Activations