© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37704
    Prev
    Next
    INDEX
    Explanations

    recipient 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
    Not in Any Lists

    No Comments

    Negative Logits
    èĮĤ
    -0.09
    æĢ»éĺŁ
    -0.09
    éļĨ
    -0.09
    åįļæĸĩ
    -0.09
    å®Įå·¥
    -0.09
    éĿ¢çĽ®
    -0.08
    timing
    -0.08
    éĺµåľ°
    -0.08
    æīĢåģļçļĦ
    -0.08
    å¸Ĥåľºè§Ħ模
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    ä¸ĢæľŁ
    0.09
    uteur
    0.09
    æľ¬æľŁ
    0.08
    eurs
    0.08
    ufe
    0.08
    åªļ
    0.08
    è¿Ħä»Ĭ
    0.08
    èķī
    0.08
    åıĪæĺ¯
    0.08
    Activations Density 0.028%

    No Known Activations