© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 694
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
    Negative Logits
    munition
    -0.09
    iali
    -0.09
    æĨĭ
    -0.09
    çĪĨ
    -0.09
    èªī
    -0.09
    çĽĺ
    -0.08
    è¿ľæĻ¯
    -0.08
    Drv
    -0.08
    kdir
    -0.08
     aprove
    -0.08
    POSITIVE LOGITS
    æĹłè®º
    0.28
    ä¸į论
    0.27
    ä¸į管
    0.26
    ä¸įç®¡ä½ł
    0.22
    æĹłè®ºæĺ¯
    0.21
     regardless
    0.20
    ä¸į管æĺ¯
    0.20
    çĦ¡è«ĸ
    0.20
    åĵªæĢķ
    0.19
    åĵªæĢķæĺ¯
    0.18
    Activations Density 0.066%

    No Known Activations