© 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. 61792
    Prev
    Next
    INDEX
    Explanations

    away from

    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
    ç«Łæĺ¯
    -0.10
    羣çļĦæĺ¯
    -0.10
    çĻ½å¤©
    -0.09
    æŶæŶ
    -0.09
    çĹ¼
    -0.08
    çģı
    -0.08
    ç´łæĿIJ
    -0.08
     rou
    -0.08
    羣æĺ¯
    -0.08
    å·²æĺ¯
    -0.08
    POSITIVE LOGITS
    éĤ£æ¬¡
    0.10
    æľīå¾ħ
    0.10
     away
    0.10
    æĪĸå¤ļ
    0.09
    å«Įå¼ĥ
    0.09
    _scalar
    0.09
    å¿ħä¸įåı¯
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.09
    iated
    0.08
    éĵĻ
    0.08
    Activations Density 0.053%

    No Known Activations