© 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. 34364
    Prev
    Next
    INDEX
    Explanations

    oral mucosa and related conditions

    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¢ĥ
    -0.10
    urch
    -0.09
    èŁ¹
    -0.09
    æ¢Ĺ
    -0.09
    误导
    -0.09
    ä½£
    -0.09
     cere
    -0.09
    лÑİд
    -0.08
     Listing
    -0.08
    ç³ķ
    -0.08
    POSITIVE LOGITS
    æ¾ľ
    0.10
    uhl
    0.09
    éģ½
    0.09
    è°´
    0.09
    çĩ¥
    0.09
    é¢Ĭ
    0.09
    åīIJ
    0.09
    ä¸ĢéĿ¢
    0.08
     cyc
    0.08
    åī¥ç¦»
    0.08
    Activations Density 0.139%

    No Known Activations