© 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. 39957
    Prev
    Next
    INDEX
    Explanations

    as a / an

    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
    Ừ
    -0.09
     comer
    -0.09
    èĥ½å¾ĹåĪ°
    -0.09
    è¿Ļä¹Łæĺ¯
    -0.08
    ivent
    -0.08
    CONS
    -0.08
    大æĪĺ
    -0.08
    æĸ°æµªå¾®åįļ
    -0.08
    秣æĪ¿
    -0.08
    纵
    -0.08
    POSITIVE LOGITS
    ä¸Ģ家
    0.11
    ä½ľä¸º
    0.09
    佶
    0.09
    5
    0.09
    å½ĵåģļ
    0.09
    éĥ½è§īå¾Ĺ
    0.08
    èµ·äºĨ
    0.08
    åIJ¯
    0.08
    atl
    0.08
    redi
    0.08
    Activations Density 0.076%

    No Known Activations