© 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. 28087
    Prev
    Next
    INDEX
    Explanations

    hair styles

    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
    èĥĥåı£
    -0.10
    çĪ¶åŃIJ
    -0.10
    éĩİå¤ĸ
    -0.09
    èĢģåŃIJ
    -0.09
    æ¶ĪåĮĸ
    -0.09
    ç¥ŀéĢļ
    -0.09
    å§Ĩ
    -0.09
    emean
    -0.08
    ìĩł
    -0.08
    æijĨåľ¨
    -0.08
    POSITIVE LOGITS
     hairst
    0.14
    梳
    0.13
    ç¾İ容
    0.12
     hair
    0.12
    Hair
    0.12
    头çļ®
    0.11
     волоÑģ
    0.11
    çIJĨåıij
    0.11
    èĦ±åıij
    0.11
    å¦Ĩ
    0.11
    Activations Density 0.070%

    No Known Activations