© 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. 49953
    Prev
    Next
    INDEX
    Explanations

    copyright / journal names

    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¦ĤæľŁ
    -0.09
    æī§æ³ķ人åijĺ
    -0.08
    ä½£
    -0.08
    antor
    -0.08
    LV
    -0.08
    追
    -0.08
    åı¤äºº
    -0.08
    åĴĮå°ļ
    -0.07
    åĿİ
    -0.07
    anto
    -0.07
    POSITIVE LOGITS
     journals
    0.10
    æľŁåĪĬ
    0.10
     tạp
    0.09
    spark
    0.09
     journal
    0.09
    Charset
    0.09
    ç¤¾åĽ¢
    0.09
     Aust
    0.09
    uala
    0.09
    åķĨæĬ¥
    0.09
    Activations Density 0.031%

    No Known Activations