© 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. 55038
    Prev
    Next
    INDEX
    Explanations

    method to determine

    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
    å¿ĥæĢĿ
    -0.10
    ä¸Ģ款
    -0.09
     näch
    -0.09
    æį¢ä¸ª
    -0.09
    ä½ĨæĪij
    -0.09
    -spe
    -0.09
    town
    -0.09
    æĺ¯ä¸Ģ款
    -0.08
    æĪijä¸Ģ缴
    -0.08
    é¾Ħ
    -0.08
    POSITIVE LOGITS
    æľ½
    0.11
    jer
    0.10
    è·Łè¸ª
    0.09
    辩
    0.09
     intern
    0.09
     track
    0.08
     easily
    0.08
     Ñĥзн
    0.08
    cape
    0.08
     rer
    0.08
    Activations Density 0.289%

    No Known Activations