© 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. 61573
    Prev
    Next
    INDEX
    Explanations

    as you may know

    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
    epy
    -0.10
    arella
    -0.09
     ÑĤоже
    -0.09
    èĪįä¸įå¾Ĺ
    -0.09
    lasses
    -0.09
    activ
    -0.09
    LAS
    -0.08
    featured
    -0.08
    globals
    -0.08
    YTE
    -0.08
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.09
    ä¸ĩåĪĨ
    0.09
    åłĥ
    0.08
    رÙĬب
    0.08
    TP
    0.08
    ä½ĵéĩı
    0.08
    ä¸įå°½
    0.08
    åIJ¬çĿĢ
    0.08
    éľŃ
    0.08
    ä¹ĭ声
    0.08
    Activations Density 0.034%

    No Known Activations