© 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. 61718
    Prev
    Next
    INDEX
    Explanations

    deficits, problems, issues, flaws, response, expression

    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
     ниÑħ
    -0.10
    ä»Ģ麽
    -0.09
    .Misc
    -0.09
    /of
    -0.08
    .Strict
    -0.08
     него
    -0.08
    ä¸Ģå®ļèĥ½
    -0.08
    è¿Ļ件äºĭæĥħ
    -0.08
    æŃ£å¼ıåIJ¯åĬ¨
    -0.08
    就好äºĨ
    -0.08
    POSITIVE LOGITS
    æĵ¢
    0.09
    ient
    0.08
    _HAL
    0.08
    atted
    0.08
    ndx
    0.08
    riter
    0.08
    allet
    0.08
    à¹ĥà¸Ļà¸ģาร
    0.08
    ickt
    0.08
    好åĩłä¸ª
    0.08
    Activations Density 1.113%

    No Known Activations