© 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. 22291
    Prev
    Next
    INDEX
    Explanations

    underwear and lingerie

    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
    è¿Ĥ
    -0.10
    æĹħéĢĶ
    -0.09
    ĥģ
    -0.09
     Kob
    -0.09
    ovich
    -0.09
    udded
    -0.09
    å¤ĸéĥ¨
    -0.09
    à¸ŀา
    -0.08
    ä¸ĭ鼨
    -0.08
    dsn
    -0.08
    POSITIVE LOGITS
    为æĤ¨
    0.09
    ç¾ŀ
    0.09
    é¨
    0.08
    á»Ĺi
    0.08
    inges
    0.08
    egrated
    0.08
    \xf
    0.08
    lemn
    0.08
    _CLAMP
    0.08
     Prim
    0.08
    Activations Density 0.003%

    No Known Activations