© 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. 18604
    Prev
    Next
    INDEX
    Explanations

    new or hot updates/news

    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
    å½»åºķ
    -0.11
    å¾¹
    -0.09
    éģĩ
    -0.08
    åĬ©
    -0.08
    绵
    -0.08
    oser
    -0.08
    smith
    -0.08
    社ä¼ļèµĦæľ¬
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
    æŁIJç§įç¨ĭ度
    -0.08
    POSITIVE LOGITS
    åĤ¬
    0.11
    aram
    0.09
    amac
    0.09
    æѤåĪ»
    0.09
    åĤ²
    0.09
    linger
    0.09
    /meta
    0.09
    åĢ¼å¾Ĺåħ³æ³¨
    0.09
    ä¸¤å¼ł
    0.09
    elan
    0.09
    Activations Density 0.030%

    No Known Activations