© 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. 37772
    Prev
    Next
    INDEX
    Explanations

    are here

    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®°ä½ı
    -0.10
    HECK
    -0.09
    èĴ¸æ±½
    -0.09
    LING
    -0.08
    æĽĽ
    -0.08
    LLU
    -0.08
    对ä»ĸ们
    -0.08
    asu
    -0.08
    _HC
    -0.08
    recht
    -0.08
    POSITIVE LOGITS
    éĹ¯
    0.09
    æĦıæĢĿæĺ¯
    0.08
     Kumar
    0.08
    ä¸įåħģ许
    0.08
    åľ¨æĪij
    0.08
    踩
    0.07
    æ¶ĤæĬ¹
    0.07
    пал
    0.07
    说åĪ°è¿ĻéĩĮ
    0.07
    Combat
    0.07
    Activations Density 0.120%

    No Known Activations