© 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. 27089
    Prev
    Next
    INDEX
    Explanations

    Roman numeral suffixes and Jr

    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
    annel
    -0.10
    ä¹ĭæīĢ
    -0.09
    èĬĻ
    -0.09
    ishop
    -0.08
    beg
    -0.08
    æĹ¢æľī
    -0.08
    ç¾Ĭæ¯Ľ
    -0.08
    ðŁijģ
    -0.08
    eam
    -0.08
    Ñĥк
    -0.08
    POSITIVE LOGITS
    åľ¨æ¸¸æĪıä¸Ń
    0.09
     aÅŁaģıd
    0.09
    æĹłç©·
    0.08
    被æī§è¡Į
    0.08
    æľīä¿¡å¿ĥ
    0.08
    rit
    0.08
    æħİ
    0.07
    ä¸įè¿ľ
    0.07
    éĴ
    0.07
    cko
    0.07
    Activations Density 0.017%

    No Known Activations