© 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. 40069
    Prev
    Next
    INDEX
    Explanations

    points off percent slam-dunk hitting in Barcelona

    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
    ith
    -0.11
     Predictor
    -0.10
    èµĽ
    -0.10
    è³½
    -0.09
    uros
    -0.09
    maker
    -0.09
     Bernardino
    -0.09
    emons
    -0.08
    è°ģçŁ¥éģĵ
    -0.08
    æݨéĢģ
    -0.08
    POSITIVE LOGITS
    ä¸ĩåįĥ
    0.09
     кап
    0.08
     unre
    0.08
    æīĢåľ¨åľ°
    0.08
    _ub
    0.08
    uba
    0.08
    å½ĵäºĭ
    0.08
     Ye
    0.08
    ä¸Ģå¤Ħ
    0.08
    avy
    0.08
    Activations Density 0.031%

    No Known Activations