© 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. 5513
    Prev
    Next
    INDEX
    Explanations

    the same

    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
    åĨĴçĿĢ
    -0.10
    åį°è±¡æ·±åĪ»
    -0.10
    åĥĸ
    -0.09
    çļĦä¿¡å¿ĥ
    -0.09
    ä¸ĭä¸ĢæŃ¥
    -0.09
    ä¿¡å¿ĥ
    -0.09
    碰åĪ°
    -0.09
    ä¸Ģæĺ¯
    -0.09
    æł¹æľ¬
    -0.09
    çļĦç»ıåħ¸
    -0.09
    POSITIVE LOGITS
     applies
    0.11
    éģĵçIJĨ
    0.10
    ä»İå°ı
    0.09
     влад
    0.08
    Ñĥк
    0.08
    Ñĥн
    0.08
    èĹ
    0.08
    è¦Ĩ
    0.08
     apply
    0.08
     ÑĤакже
    0.08
    Activations Density 0.024%

    No Known Activations