© 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. 35219
    Prev
    Next
    INDEX
    Explanations

    ovarian cancer

    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·±è¿ľ
    -0.09
    身å¿ĥ
    -0.09
    ively
    -0.09
     elabor
    -0.09
    ä¸į失
    -0.09
    udy
    -0.09
    otte
    -0.09
    éĤ£ä¸ªäºº
    -0.08
    Ñĥд
    -0.08
     Shirley
    -0.08
    POSITIVE LOGITS
    ç³ł
    0.10
    çݺ
    0.10
    ä»ħæľī
    0.09
    ÙĤ
    0.09
    craft
    0.08
    ä¹Łåıªæľī
    0.08
    çıįçıł
    0.08
    رز
    0.08
    çıij
    0.08
    holder
    0.08
    Activations Density 0.022%

    No Known Activations