© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8654
    Prev
    Next
    INDEX
    Explanations

    Circuit Judges

    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
    ä¿Ĺ称
    -0.09
    èĢģåŃĹåı·
    -0.08
    è®°ä½ı
    -0.08
    åĵªæĢķæĺ¯
    -0.08
    pler
    -0.07
    éģµå®Ī
    -0.07
    å½¢å¼ı
    -0.07
     behalf
    -0.07
     eventual
    -0.07
    ä½ĵçİ°
    -0.07
    POSITIVE LOGITS
    æī§
    0.11
    为é¦ĸçļĦ
    0.11
    éĻ¢å£«
    0.10
    导读
    0.09
    缺å¸Ń
    0.09
    ä¸īä½į
    0.09
     Voor
    0.09
    invisible
    0.09
    issy
    0.09
    PRESENT
    0.08
    Activations Density 0.180%

    No Known Activations