© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 611
    Prev
    Next
    INDEX
    Explanations

    ç, çľ®, 说, 追, æĹł, 说, 追, æĹł, middle, How, digital, ited, for, č

    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
    Negative Logits
    çİ»
    -0.08
    é¢ģ
    -0.08
    Lux
    -0.08
    ìĿ¸ì§Ģ
    -0.08
    å·¾
    -0.08
    表彰
    -0.08
    rv
    -0.08
    éĤ£ç§į
    -0.08
     mv
    -0.08
    æŁ±
    -0.08
    POSITIVE LOGITS
    èįĴ
    0.10
    èĦijæµ·
    0.09
    缮çļĦåľ¨äºİ
    0.09
    ä¾µæĿĥ
    0.09
    说æĪij
    0.09
    追究
    0.09
    æĹłæĦı
    0.09
    yre
    0.09
    roma
    0.09
    FullYear
    0.08
    Activations Density 0.269%

    No Known Activations