© 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. 32611
    Prev
    Next
    INDEX
    Explanations

    cost more than

    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
    èĥĮåIJİ
    -0.09
    迹象
    -0.09
    éĢģåİ»
    -0.09
    æ´¾åĩº
    -0.09
    kah
    -0.08
    CAS
    -0.08
    AWN
    -0.08
    oor
    -0.08
    vla
    -0.08
    oad
    -0.08
    POSITIVE LOGITS
    ä¸įå°ı
    0.10
    å§Ķ
    0.09
    äºĽ
    0.09
     sob
    0.09
    ç´Ĭä¹±
    0.08
    代价
    0.08
    转åŀĭåįĩ级
    0.08
     dearly
    0.08
    建设åĴĮ
    0.08
    é¦ĸä»ĺ
    0.08
    Activations Density 0.019%

    No Known Activations