© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52251
    Prev
    Next
    INDEX
    Explanations

    etc or /or

    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
    äººåľ¨
    -0.09
    IMS
    -0.09
    缮çļĦåľ¨äºİ
    -0.08
    èĢĮè¿Ļ
    -0.08
    à¸ĩ
    -0.08
    æĸ¯åŁº
    -0.08
    ç»´å¥ĩ
    -0.08
    åĮĿ
    -0.08
    èĴľ
    -0.07
    åij¼
    -0.07
    POSITIVE LOGITS
    apos
    0.10
     etc
    0.10
    åĩ¡æľ¬ç½ij
    0.09
    ãģıãĤĮ
    0.09
    ä¸į容æĺĵ
    0.08
    /or
    0.08
    ç®į
    0.08
    ä»Ģä¹Īåij¢
    0.08
     bÄħdź
    0.08
    ķ
    0.08
    Activations Density 0.284%

    No Known Activations