© 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. 21539
    Prev
    Next
    INDEX
    Explanations

    hairy surface, leaves, or polarity

    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
    åįĥéĩĮ
    -0.11
    æIJŃ
    -0.10
    ãĤĴè¦ĭãĤĭ
    -0.10
    æ³ķ人
    -0.09
    éĨĴ
    -0.09
    æĮ½
    -0.09
    表彰
    -0.08
    è·Łè¿Ľ
    -0.08
    çł£
    -0.08
    åŁºéĩijä¼ļ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæīĭ
    0.11
    ç¦
    0.10
     pró
    0.09
    è¾¹
    0.09
    åĴĮå¹³
    0.09
    æİ¥åıĹäºĨ
    0.09
    ä¸ĢéĿ¢
    0.09
    apan
    0.09
    apl
    0.08
    éĿ¢ä¸Ĭ
    0.08
    Activations Density 0.126%

    No Known Activations