© 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. 2841
    Prev
    Next
    INDEX
    Explanations

    using or editing documentation

    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
    çĭĤ
    -0.09
    uby
    -0.09
    èµģ
    -0.08
    çī¹æ®Ĭ
    -0.08
    è£ħå¤ĩåĪ¶éĢł
    -0.08
    åīįè¿°
    -0.08
    æĪIJ为ä¸ŃåĽ½
    -0.08
    ç»Ħç»ĩå®ŀæĸ½
    -0.08
    arto
    -0.08
    èħ´
    -0.08
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.11
     пÑĢавилÑĮно
    0.11
     correctly
    0.11
    ä¸įè¦ģ太
    0.11
     only
    0.11
    æŃ£ç¡®çļĦ
    0.11
     properly
    0.10
    å®ŀäºĭæ±Ĥæĺ¯
    0.10
    æŃ£ç¡®
    0.10
     rather
    0.10
    Activations Density 0.352%

    No Known Activations