© 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. 54998
    Prev
    Next
    INDEX
    Explanations

    more of a/an

    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
    æİıåĩº
    -0.09
    istas
    -0.09
    åªĴä½ĵæĬ¥éģĵ
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    çļĦå°±æĺ¯
    -0.09
     Tin
    -0.08
     componentDidUpdate
    -0.08
    åħĨ
    -0.08
    棣
    -0.08
    à¹Į
    -0.08
    POSITIVE LOGITS
    ä¸īæĸ¹
    0.10
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    ä¸Ģ个èģĮä¸ļ
    0.10
    erial
    0.10
    æĥ³æ³ķ
    0.10
    äºļ马
    0.09
    usc
    0.09
    ãģĻãĤĭãģĵãģ¨ãģ¯
    0.09
    ä¸Ģ个å¤ļ
    0.09
    THING
    0.09
    Activations Density 0.004%

    No Known Activations