© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16919
    Prev
    Next
    INDEX
    Explanations

    . words

    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
    éĶĻ
    -0.10
    èĻĶ
    -0.10
    æīįèĥ½å¤Ł
    -0.10
    é¢ĨåĨĽ
    -0.10
    æīĢä»¥åľ¨
    -0.09
    彩èĻ¹
    -0.09
    è¿«ä¸įåıĬå¾ħ
    -0.09
    èµ
    -0.09
    éĮ¯
    -0.09
    èĢĮä¸Ķ
    -0.09
    POSITIVE LOGITS
     xsi
    0.09
    antine
    0.09
    å±ıå¹ķä¸Ĭ
    0.08
    emics
    0.08
     Hamm
    0.08
    (Camera
    0.08
    çļĦèĢģ
    0.08
    à¸Ļาม
    0.08
    è¿ĻéĩĮæĺ¯
    0.08
    .esp
    0.08
    Activations Density 0.039%

    No Known Activations