© 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. 26686
    Prev
    Next
    INDEX
    Explanations

    lists starting with (a) or (b)

    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
    æĺ¯ä¸Ģ件
    -0.10
    ä¹Łä¸įåı¯èĥ½
    -0.10
    说æĺ¯
    -0.10
    ucker
    -0.10
    æĺ¯ä¸Ģ座
    -0.10
    è¿Ļ让
    -0.10
    åĴĮå®ĮåĸĦ
    -0.09
    è¯ģçĽij
    -0.09
    æ¶Īæģ¯ç§°
    -0.09
    表æĥħ
    -0.09
    POSITIVE LOGITS
     Ruiz
    0.09
    shaft
    0.09
    -hide
    0.07
    sets
    0.07
    åĬłæ·±
    0.07
    /classes
    0.07
    à¹Į
    0.07
     invis
    0.07
    arus
    0.07
     gem
    0.07
    Activations Density 0.136%

    No Known Activations