© 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. 32889
    Prev
    Next
    INDEX
    Explanations

    declined to

    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
    miss
    -0.10
    ä¸įæĸŃåľ°
    -0.09
    .yahoo
    -0.08
    ä¸į幸
    -0.08
    缮çļĦåľ¨äºİ
    -0.08
    (comb
    -0.08
    civil
    -0.08
    åĴ»
    -0.08
    ä¸įåŃĺåľ¨
    -0.08
    lov
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
    詳
    0.10
     hẳn
    0.10
    èģĬèģĬ
    0.09
    æĶ¾è¿ĩ
    0.09
    åĪĨå·¥
    0.09
    ç»ĦåĽ¢
    0.09
    èµ´
    0.09
    arie
    0.09
    æ£ł
    0.09
    Activations Density 0.003%

    No Known Activations