© 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. 37267
    Prev
    Next
    INDEX
    Explanations

    menopause

    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
    ä¹Łåıªèĥ½
    -0.09
    ment
    -0.09
    åı¯è§Ĥ
    -0.09
    æľīæķĪçļĦ
    -0.09
    ments
    -0.08
    贯彻
    -0.08
    泡沫
    -0.08
    æī©
    -0.08
    Ñıм
    -0.08
    jes
    -0.08
    POSITIVE LOGITS
    女人
    0.11
    å¦ĩ女
    0.10
    çĶ·äºº
    0.10
    æ¡ħ
    0.09
     women
    0.09
    fiction
    0.09
    -friendly
    0.09
    æķĻè®Ń
    0.09
    ä¹ĭæĹħ
    0.08
    бÑĢо
    0.08
    Activations Density 0.030%

    No Known Activations