© 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. 57595
    Prev
    Next
    INDEX
    Explanations

    proceeds of crime, accomplices, helped raid

    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
    æĻĭ级
    -0.10
    æĹłå¿§
    -0.10
    æĻĭåįĩ
    -0.10
    贵宾
    -0.10
    æĪĺèĥľ
    -0.09
    礼çī©
    -0.09
    ingleton
    -0.09
    æĥĬåĸľ
    -0.09
    èµłéĢģ
    -0.09
    èĥ½åģļåĪ°
    -0.09
    POSITIVE LOGITS
    èµĥ
    0.14
    ä½ľæ¡Ī
    0.13
    åĪĨåŃIJ
    0.10
    被æįķ
    0.09
    çĬ¯ç½ª
    0.09
    deen
    0.09
    çİ°åľº
    0.09
    è¯ģæį®
    0.08
    RACT
    0.08
    罪
    0.08
    Activations Density 0.061%

    No Known Activations