© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47561
    Prev
    Next
    INDEX
    Explanations

    check in or record

    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
    Negative Logits
    èĬĤ
    -0.09
    èĨº
    -0.09
    å¿Ĺ强
    -0.09
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    ä¸įéĢļ
    -0.09
    å£ij
    -0.08
    éĽ³
    -0.08
    åħ¨åĽ½äººå¤§
    -0.08
    leases
    -0.08
    ä¸Ģ缴å¤Ħäºİ
    -0.08
    POSITIVE LOGITS
    æīĵåį¡
    0.14
    è¿Ľåĩº
    0.11
    æĹ·
    0.10
    åĩ«
    0.10
    è®°å½ķ
    0.10
    åĩºåħ¥
    0.10
    泯
    0.09
    éĴ¤
    0.09
    è¿ĽéŨ
    0.09
    zon
    0.09
    Activations Density 0.080%

    No Known Activations