© 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. 34833
    Prev
    Next
    INDEX
    Explanations

    for the less

    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
    åıĭ们
    -0.09
    大å¤ļæĺ¯
    -0.08
    à¸ģระà¸Ī
    -0.08
    å¾Ģå¾Ģä¼ļ
    -0.08
     Guard
    -0.08
    æ¯ıä¸Ģ次
    -0.08
    æģķ
    -0.08
     rotary
    -0.08
    éĴµ
    -0.08
    ä½ľä¸ºä¸ĢåIJį
    -0.08
    POSITIVE LOGITS
    å¿ĥçģµ
    0.10
    èĥĨ
    0.10
     ath
    0.09
    adt
    0.09
    ride
    0.09
     Oaks
    0.08
    èĤ¯
    0.08
    æĢĢæĬ±
    0.08
    é¢Ħ订
    0.08
    ithe
    0.08
    Activations Density 0.060%

    No Known Activations