© 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. 50302
    Prev
    Next
    INDEX
    Explanations

    ovulatory cycles

    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
    çĺª
    -0.09
    -anchor
    -0.09
    飽
    -0.09
    è°¦
    -0.09
    人家
    -0.08
    å¸Ī
    -0.08
    财产
    -0.08
    âİĿ
    -0.08
    åį´åıĪ
    -0.08
    æķ£
    -0.08
    POSITIVE LOGITS
    ichel
    0.09
     ov
    0.09
    ogui
    0.09
    ä¸įåħ·å¤ĩ
    0.08
    æıª
    0.08
    æĥŃ
    0.08
    ç¾ģ
    0.08
    çıł
    0.08
    tsy
    0.08
    ç½ķ
    0.08
    Activations Density 0.072%

    No Known Activations