© 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. 62639
    Prev
    Next
    INDEX
    Explanations

    sexual arousal

    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
    èĢĻ
    -0.09
    æĸ¹éĴĪ
    -0.09
    opper
    -0.09
    羣å¿ĥ
    -0.08
    åĮłå¿ĥ
    -0.08
    温馨
    -0.08
    RAIN
    -0.08
    éĵ¿
    -0.08
    æŃĩ
    -0.08
     erv
    -0.08
    POSITIVE LOGITS
    æĹºçĽĽ
    0.10
    Hur
    0.09
    обÑħодим
    0.09
    atos
    0.09
    身穿
    0.09
    æĬ½åĩº
    0.09
    hots
    0.09
     #+#
    0.09
    å¾Ĺä½ı
    0.09
    /de
    0.09
    Activations Density 0.007%

    No Known Activations