© 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. 11260
    Prev
    Next
    INDEX
    Explanations

    unequal, uneven, asymmetric

    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
    çĽ¸å¯¹è¾ĥ
    -0.09
    éĢĢ
    -0.08
     Patt
    -0.08
    çĪIJ
    -0.08
    ä¸į容æĺĵ
    -0.08
    äºĶå¹´
    -0.08
    à°¬
    -0.08
    xDF
    -0.08
     Carlo
    -0.08
    æĿ¥è®²
    -0.08
    POSITIVE LOGITS
    ä¸į平衡
    0.14
    累累
    0.10
    ä¸Ģç«Ļ
    0.10
    æ±Łæ·®
    0.09
    éķ¿çŁŃ
    0.09
     unequal
    0.09
    ä¸Ģè¾¹
    0.09
    åIJĦéĥ¨éŨ
    0.09
     uneven
    0.09
    _CS
    0.09
    Activations Density 0.122%

    No Known Activations