© 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. 26995
    Prev
    Next
    INDEX
    Explanations

    providing information on opportunities

    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
    Winner
    -0.10
    çİ¥
    -0.09
    éģį
    -0.09
    æĹłæĦı
    -0.08
    èµĽåIJİ
    -0.08
    ä¸įçŁ¥ä¸įè§ī
    -0.08
    éģĹ
    -0.08
     An
    -0.08
    ä¸įåģľåľ°
    -0.08
    ÙĦØ·
    -0.08
    POSITIVE LOGITS
    å±ĬæŶ
    0.29
    åĪ°æŶåĢĻ
    0.21
    é¢Ħ计å°Ĩ
    0.19
    å°Ĩäºİ
    0.18
    å°Ĩåľ¨
    0.18
    é¢Ħ计
    0.18
    å°Ĩä¼ļ
    0.17
    åį³å°Ĩ
    0.16
    åį³å°ĨåĪ°æĿ¥
    0.16
    å°Ĩæĺ¯
    0.16
    Activations Density 0.145%

    No Known Activations