© 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. 34761
    Prev
    Next
    INDEX
    Explanations

    understand why

    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
    PLE
    -0.09
    çĽ¸å¯¹è¾ĥ
    -0.09
    èł¡
    -0.09
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
    fur
    -0.09
    ÑĢÑĥд
    -0.09
    åĨ¶
    -0.09
    èĢħãģ¯
    -0.09
    èĥ¡åŃIJ
    -0.09
    @qq
    -0.08
    POSITIVE LOGITS
    æĤŁ
    0.09
    é¢ĨæĤŁ
    0.09
    ä¸ĭæĿ¥
    0.09
    ongs
    0.08
    é¢Ĩä¼ļ
    0.08
    认è¯ĨåĪ°
    0.08
    è½
    0.08
    cen
    0.08
     Mein
    0.08
    ctor
    0.08
    Activations Density 0.060%

    No Known Activations