© 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. 32279
    Prev
    Next
    INDEX
    Explanations

    Copyright year and licenses

    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
     handing
    -0.08
    è¯Ŀ说
    -0.08
    æĢ»èµĦ产
    -0.07
    访
    -0.07
    otation
    -0.07
    åĮ»çĶ¨
    -0.07
    .pdf
    -0.07
    Ì
    -0.07
    åī¯ä¹¦è®°
    -0.07
     NIH
    -0.07
    POSITIVE LOGITS
    $core
    0.10
    ATAR
    0.09
    äºĨæĪijçļĦ
    0.09
    amac
    0.09
    éĸī
    0.09
    ä¸įå¾Ĺå·²
    0.09
     rhet
    0.08
    /ay
    0.08
    hani
    0.08
    ä¸ŃåĽ½ä¼ģä¸ļ
    0.08
    Activations Density 0.097%

    No Known Activations