© 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. 52679
    Prev
    Next
    INDEX
    Explanations

    brunette, blonde, haired descriptions

    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
    åIJĦ大
    -0.09
     dull
    -0.08
    èĿ¾
    -0.08
    æIJª
    -0.08
    inski
    -0.08
    åįķ车
    -0.07
     itself
    -0.07
     Lone
    -0.07
    éĶ£
    -0.07
    é¾¢
    -0.07
    POSITIVE LOGITS
    ixin
    0.09
    -haired
    0.09
    èĤ¤
    0.09
     haired
    0.09
    éĢŀ
    0.09
    ght
    0.09
     Opr
    0.08
    ÕŃ
    0.08
    [url
    0.08
    bern
    0.08
    Activations Density 0.011%

    No Known Activations