© 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. 51207
    Prev
    Next
    INDEX
    Explanations

    said or uttered discourse

    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
    太éĺ³åŁİ
    -0.09
    å¦Ħ
    -0.09
    çľĭ好
    -0.09
    çĤ¹æ»´
    -0.08
    æīĵ交éģĵ
    -0.08
    åIJĦæľī
    -0.08
    éĥ½æĹłæ³ķ
    -0.08
    abby
    -0.08
    æ´Ĺ礼
    -0.08
    æĥ³çĿĢ
    -0.08
    POSITIVE LOGITS
    对æĪij说
    0.14
    ç¬ijçĿĢ说
    0.14
    说éģĵ
    0.13
    åľ°è¯´
    0.13
    æĮĩçĿĢ
    0.12
    äºĨä¸Ģåı¥
    0.11
    ä»ĸ说
    0.11
    ç«ŁçĦ¶
    0.10
    ä¸Ģåı¥
    0.10
    æİıåĩº
    0.10
    Activations Density 0.040%

    No Known Activations