© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    recording achievements and results

    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
    æİ¥åĬĽ
    -0.10
    æİīäºĨ
    -0.10
    æĹ¶æľº
    -0.09
    æĬ¥è®°èĢħ
    -0.09
    çĸij
    -0.09
    è¾ĵäºĨ
    -0.09
    	ST
    -0.09
    俯
    -0.09
    yal
    -0.08
    inia
    -0.08
    POSITIVE LOGITS
    å¥Ī
    0.10
    æĿ
    0.08
    WI
    0.08
    åľ¨å¤ĸéĿ¢
    0.08
    åĩ»æĿĢ
    0.08
    Drv
    0.08
    çĭ¬ä¸ĢæĹłäºĮ
    0.08
    éĦĦ
    0.08
    è¦Ĩ
    0.08
    redentials
    0.08
    Activations Density 0.014%

    No Known Activations