© 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. 32692
    Prev
    Next
    INDEX
    Explanations

    not come, not give, not work

    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
    å½ĵçĦ¶
    -0.13
     Garr
    -0.09
     اÙĦØ°
    -0.09
    ä»ħä»ħæĺ¯
    -0.09
    åĢĴæĺ¯
    -0.09
    ä¹Łè®¸
    -0.09
    å½ĵçĦ¶æĺ¯
    -0.09
    éĩijèī²
    -0.09
    ä¹Łè®¸æĺ¯
    -0.09
    çķ¶çĦ¶
    -0.09
    POSITIVE LOGITS
    ç½ij讯
    0.09
     elev
    0.09
    sett
    0.08
    åŃĺåľ¨çĿĢ
    0.08
     anymore
    0.08
    åĭł
    0.08
    ystore
    0.08
    æį¶
    0.08
    æ¸ĹéĢı
    0.08
    å¥ĭ
    0.08
    Activations Density 0.021%

    No Known Activations