© 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. 40090
    Prev
    Next
    INDEX
    Explanations

    may or might

    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¿Ļæł·åģļ
    -0.10
    è¿Ļä¹Īåģļ
    -0.09
    pest
    -0.09
    Ñĥг
    -0.09
    æĥ©
    -0.09
    orer
    -0.09
    èĹī
    -0.08
    é¢ĦæĸĻ
    -0.08
    è¿ĻçĤ¹
    -0.08
    åģļåĪ°
    -0.08
    POSITIVE LOGITS
    æĬķåħ¥åĪ°
    0.11
    æĺĵäºİ
    0.11
    æĽ´å®¹æĺĵ
    0.11
    容æĺĵ
    0.10
    æĬķ身
    0.10
    åĨįåİ»
    0.10
    å·¥ä½ľæķĪçİĩ
    0.09
    åIJİç»Ń
    0.09
    å¥ĭ
    0.09
    åıªæĥ³
    0.09
    Activations Density 0.150%

    No Known Activations