© 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. 47982
    Prev
    Next
    INDEX
    Explanations

    Dominic, Dominik, Dominican, Dominion

    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
    å¥ĭè¿Ľ
    -0.10
    inine
    -0.10
    oha
    -0.09
    管å§Ķä¼ļ
    -0.09
    weet
    -0.09
    plode
    -0.09
    رÙģ
    -0.08
    é¹ģ
    -0.08
    æ·±åİļçļĦ
    -0.08
    ä¸ĢåŃĹ
    -0.08
    POSITIVE LOGITS
    ality
    0.09
    ustr
    0.09
    èĥĽ
    0.09
    åľ°ä½į
    0.08
    uet
    0.08
    ì§ĵ
    0.08
    SSION
    0.08
    ç¹ĩ
    0.08
    ael
    0.08
    adel
    0.08
    Activations Density 0.011%

    No Known Activations