© 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. 32009
    Prev
    Next
    INDEX
    Explanations

    copyright license"}

    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
     thú
    -0.09
    çºĤ
    -0.09
    èĻ¬
    -0.09
    æ¨Ĭ
    -0.09
    èĢĥåı¤
    -0.09
    å¿ĥçIJĨåĴ¨è¯¢
    -0.08
    主åħ¬
    -0.08
    /gpl
    -0.08
    vens
    -0.08
    主åĭķ
    -0.08
    POSITIVE LOGITS
    ä¹ĭæīĢ以
    0.09
    æĸĭ
    0.09
    è¦ģåѦä¼ļ
    0.09
    èĦ±ç¦»
    0.08
    isci
    0.08
    WebRequest
    0.08
    表çİ°åĩº
    0.08
    isman
    0.08
     mod
    0.08
    ahan
    0.08
    Activations Density 0.059%

    No Known Activations