© 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. 63369
    Prev
    Next
    INDEX
    Explanations

    the best / definitive

    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
    æľĢ主è¦ģ
    -0.11
    åĢĴæĺ¯
    -0.09
    æľĢéĩįè¦ģçļĦ
    -0.09
    æĦļèł¢
    -0.09
    为主ä½ĵ
    -0.09
    æľĢåħ³éĶ®
    -0.08
    å¿IJ
    -0.08
    _TEM
    -0.08
    为主è¦ģ
    -0.08
    æľĢ主è¦ģçļĦ
    -0.08
    POSITIVE LOGITS
     PROT
    0.10
    å½ĵå¹´
    0.09
    åħ¨æĹ¥
    0.09
    DEF
    0.09
    inder
    0.08
    mens
    0.08
    ail
    0.08
    æ´»å¾Ĺ
    0.08
    AIL
    0.08
    éĢĤå½ĵ
    0.08
    Activations Density 0.040%

    No Known Activations