© 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. 53566
    Prev
    Next
    INDEX
    Explanations

    full of

    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
     slightest
    -0.09
    éĤ£ä»½
    -0.09
    oro
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.08
    otal
    -0.08
    èĬŃ
    -0.08
    å¤ĸéĿ¢
    -0.08
    å¿ī
    -0.08
    æīĢåľ¨åľ°
    -0.08
    bul
    -0.08
    POSITIVE LOGITS
    enment
    0.10
    lications
    0.09
    ç»ıéªĮåĴĮ
    0.09
    æĬ¬
    0.09
    sWith
    0.09
    ë§Į
    0.08
    满满çļĦ
    0.08
    ICODE
    0.08
     compromise
    0.08
    specs
    0.08
    Activations Density 0.015%

    No Known Activations