© 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. 34806
    Prev
    Next
    INDEX
    Explanations

    . or — followed by capitalization

    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
    ä¹Łå°±æĺ¯è¯´
    -0.11
    æĶ»åĿļæĪĺ
    -0.09
    æĪĸèĢħæĺ¯
    -0.09
    çĶŁçĶŁ
    -0.08
    ream
    -0.08
    ä¹Łå°±æĺ¯
    -0.08
    aly
    -0.08
    ä½łåĸľæ¬¢
    -0.08
    imum
    -0.08
    èĽĨ
    -0.08
    POSITIVE LOGITS
    ä¹ĭæĥħ
    0.12
     ÐĴедÑĮ
    0.10
    æĪijä¹Ł
    0.09
    ectl
    0.09
    å°¤åħ¶æĺ¯
    0.09
    è¦ģçŁ¥éģĵ
    0.09
    å°¤åħ¶
    0.09
    ä¹ŁçŁ¥éģĵ
    0.09
    porto
    0.09
    ç´į
    0.08
    Activations Density 0.072%

    No Known Activations