© 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. 63697
    Prev
    Next
    INDEX
    Explanations

    contraception and birth control methods

    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
    æ§ģ
    -0.10
    osa
    -0.10
    åħij
    -0.09
    åī¡
    -0.09
    åĿIJçĿĢ
    -0.09
    åħ³æĢĢ
    -0.09
    æĸĩåĮĸåºķèķ´
    -0.09
    éĩİçĶŁåĬ¨çī©
    -0.09
    ä¸įåłª
    -0.09
    ureau
    -0.09
    POSITIVE LOGITS
    orget
    0.09
     Castro
    0.08
    è¡ĵ
    0.08
    ÑıÑģÑĮ
    0.08
    via
    0.08
    Äįe
    0.08
    à¸Ħม
    0.08
    ORB
    0.08
    æľ¯
    0.08
    athers
    0.08
    Activations Density 0.009%

    No Known Activations