© 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. 38952
    Prev
    Next
    INDEX
    Explanations

    giving a

    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
    大家ä¸Ģèµ·
    -0.09
     Gri
    -0.09
    å¤ļåįĬ
    -0.09
    è¶Ł
    -0.08
    менно
    -0.08
     нем
    -0.08
    ç»Ļ
    -0.08
    ogie
    -0.08
    ä¸įå®Į
    -0.08
     Lam
    -0.08
    POSITIVE LOGITS
     chance
    0.10
    ANCE
    0.09
     chances
    0.09
    æīĢéľĢè¦ģçļĦ
    0.09
    æľīæľºä¼ļ
    0.09
    æīĢéľĢçļĦ
    0.09
    æīĢéľĢè¦ģ
    0.09
     access
    0.09
    èĦ±ç¦»
    0.09
    çļĦä¸ĢåĪĩ
    0.09
    Activations Density 0.024%

    No Known Activations