© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    phrase to come

    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
    å¹²ä»Ģä¹Ī
    -0.09
    blank
    -0.08
    chine
    -0.08
    éĥ½è¯´
    -0.08
    建åįİ
    -0.08
    æ¼³
    -0.08
    åıªæĺ¯ä¸ºäºĨ
    -0.08
    æĥ«
    -0.08
     Ventures
    -0.08
    rose
    -0.08
    POSITIVE LOGITS
    åŃĺåľ¨äºİ
    0.13
    å°±åľ¨
    0.13
    ä½ĵçİ°åľ¨
    0.12
    éļIJèĹı
    0.10
    ä»įåľ¨
    0.10
    åıĸåĨ³äºİ
    0.10
    åľ¨äºİ
    0.10
     наÑħодиÑĤÑģÑı
    0.10
    éĢł
    0.09
    å°±åľ¨äºİ
    0.09
    Activations Density 0.153%

    No Known Activations