© 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. 48778
    Prev
    Next
    INDEX
    Explanations

    request or demand action

    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
    íĸĪëĬĶëį°
    -0.09
    涣
    -0.09
    laces
    -0.08
    æľīæŶ
    -0.08
    æľīäºĨ
    -0.08
    åı¯èĥ½ä¼ļ
    -0.08
    çķ¥æľī
    -0.08
     Nash
    -0.08
     partly
    -0.08
     usually
    -0.08
    POSITIVE LOGITS
    羣æŃ£çļĦ
    0.13
    ä¸įè¦ģåĨį
    0.12
    羣æŃ£
    0.12
    è¿Ļæīįæĺ¯
    0.12
    èµ·çłģ
    0.11
    æĹ©æĹ¥
    0.11
    åĵªæĢķ
    0.10
    éĸ£
    0.10
    åįĥä¸ĩä¸įè¦ģ
    0.10
    ä¸į顾
    0.10
    Activations Density 0.056%

    No Known Activations