© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36170
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    çļĦæĹ¥
    -0.08
    姣
    -0.08
    Kel
    -0.08
    åľ¨å½ĵåľ°
    -0.07
    èĩªçĦ¶èĢĮ
    -0.07
    å¿«æĬ¥
    -0.07
    orney
    -0.07
    åIJĦ个çݯèĬĤ
    -0.07
    bidden
    -0.07
    ä¸įä»ħèĥ½
    -0.07
    POSITIVE LOGITS
    æīįæĺ¯
    0.11
    åºĻ
    0.10
    /null
    0.10
    ä¹ŁåIJĮæł·
    0.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.09
    maal
    0.09
    æħķ
    0.09
    MAND
    0.09
    è¿Ļ让
    0.09
    éĻĦåĬł
    0.08
    Activations Density 0.154%

    No Known Activations