© 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. 2616
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and science fiction

    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
    ç¾ģ
    -0.09
    寸
    -0.09
    è°ĭ
    -0.09
    çģ¾éļ¾
    -0.09
    twig
    -0.09
    ewise
    -0.09
    çļĦåij½è¿IJ
    -0.09
    è¬Ģ
    -0.08
     maté
    -0.08
    ãģ¬
    -0.08
    POSITIVE LOGITS
    ä¼ij
    0.10
    æ´»åĬ¨ä¸Ń
    0.09
     caus
    0.09
     causal
    0.09
    åħ±åIJĮä½ĵ
    0.09
     ÐĶе
    0.08
    äºĨä¸Ģ份
    0.08
    éģ®
    0.08
    ä¸ºçĽ®çļĦ
    0.08
    èĿ½
    0.08
    Activations Density 0.106%

    No Known Activations