© 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. 2250
    Prev
    Next
    INDEX
    Explanations

    css bug or issue

    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
    为ä¹ĭ
    -0.10
    å¿ĥä¸Ń
    -0.10
    å¿ĥ缮
    -0.09
    åģļçļĦäºĭ
    -0.09
    çİĭåĽ½
    -0.09
    ä»ĸå·²ç»ı
    -0.09
    iskey
    -0.09
    失åĪ©
    -0.09
    éĤ£ä½į
    -0.09
    SAT
    -0.09
    POSITIVE LOGITS
     clo
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.09
    ä¼ļåĩºçİ°
    0.09
    æŁIJäºĽ
    0.08
    ä¸įåı¯
    0.08
    å°¤åħ¶æĺ¯åľ¨
    0.08
    æŀIJ
    0.08
     mar
    0.08
    éģĹ产
    0.08
    Compat
    0.08
    Activations Density 1.252%

    No Known Activations