© 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. 17148
    Prev
    Next
    INDEX
    Explanations

    Subscribe to, Register with, . Field

    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
    éŨæĪ·ç½ijç«Ļ
    -0.08
    æĴ®
    -0.08
    å¤Ħäºİ
    -0.08
    ä¸Ģ缴å¤Ħäºİ
    -0.08
    çļĦæķ´ä½ĵ
    -0.08
    éĿ¢çĽ®
    -0.08
    å¿ĥèĦıçĹħ
    -0.08
    éĴ
    -0.08
    åıĽ
    -0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    POSITIVE LOGITS
    çķĻ
    0.12
    åħ³æ³¨
    0.11
     horns
    0.10
     Reflex
    0.10
    æIJľ
    0.09
    _pel
    0.09
    å¯ĨåĪĩåħ³æ³¨
    0.09
    à¸Ħม
    0.09
     reflex
    0.08
    Hooks
    0.08
    Activations Density 0.015%

    No Known Activations