© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22355
    Prev
    Next
    INDEX
    Explanations

    chances of winning or succeeding

    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
    edException
    -0.09
    ugu
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
     Andre
    -0.09
    IRST
    -0.09
    Ñģко
    -0.08
    å¯¹æľªæĿ¥
    -0.08
    å¿«è¦ģ
    -0.08
    hart
    -0.08
    å¾ģæ±Ĥ
    -0.08
    POSITIVE LOGITS
    ÙĥÙĪÙĨ
    0.09
    æĪIJ为ä¸ŃåĽ½
    0.09
    å¤į
    0.09
    abh
    0.09
    æĪIJ为
    0.09
    æ³®
    0.09
    èİ·å¾ĹæĽ´å¤ļ
    0.09
    èĥľä»»
    0.09
    稳
    0.08
    avan
    0.08
    Activations Density 0.017%

    No Known Activations