© 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. 34956
    Prev
    Next
    INDEX
    Explanations

    time / period

    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
    à¹Ģสร
    -0.11
    颦
    -0.10
    椴
    -0.10
    头èĦij
    -0.10
    ãģ§ãģĬ
    -0.10
    æİ¥åıĹäºĨ
    -0.09
    åĵŃäºĨ
    -0.09
    éĿ¢ç§¯çº¦
    -0.09
    å¾Ĺå¾Ī好
    -0.09
    undle
    -0.09
    POSITIVE LOGITS
    æīĢåľ¨
    0.09
    è¾ĸåĮº
    0.09
    示èĮĥåŁºåľ°
    0.09
    çݺ
    0.09
    å®ļ
    0.09
    å½ĵåľ°çļĦ
    0.08
    åľ¨å½ĵåľ°
    0.08
    è¾ĸåĮºåĨħ
    0.08
    寡
    0.08
    åĵªå®¶
    0.08
    Activations Density 1.379%

    No Known Activations