© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    citations and downloads

    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
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.10
     Dick
    -0.10
    æģĴ
    -0.09
    è¿Ļ个æĹ¶ä»£
    -0.09
    æ»ĵ
    -0.09
    æľķ
    -0.08
    ä¸Ģ线
    -0.08
    çģµéŃĤ
    -0.08
    æ±Łæ·®
    -0.08
    æ°¸æģĴ
    -0.08
    POSITIVE LOGITS
     putt
    0.08
    ppard
    0.08
    دا
    0.08
    éĻµ
    0.08
    仲
    0.08
    åĢĺèĭ¥
    0.08
    lide
    0.07
    arend
    0.07
    éĤĢ
    0.07
    lated
    0.07
    Activations Density 0.201%

    No Known Activations