© 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. 3740
    Prev
    Next
    INDEX
    Explanations

    outside locations

    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
    æĿŁ
    -0.10
    好çİ©
    -0.10
    衬
    -0.10
    笥
    -0.10
    ç°¸
    -0.10
    èĩªèIJ¥
    -0.09
    éı¡
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.09
    STALL
    -0.09
    ç»ıèIJ¥ç®¡çIJĨ
    -0.09
    POSITIVE LOGITS
    éĺ³åħī
    0.10
    ç¿ħèĨĢ
    0.09
    éĢģ
    0.09
    翼
    0.09
    室å¤ĸ
    0.08
    iland
    0.08
    太éĺ³
    0.08
    æĻĴ
    0.08
    åİĭè¿«
    0.08
    æĻ¯èī²
    0.08
    Activations Density 0.046%

    No Known Activations