© 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. 38730
    Prev
    Next
    INDEX
    Explanations

    like this

    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
    主è¦ģæľī
    -0.10
     BMP
    -0.09
    èºģ
    -0.09
    UnderTest
    -0.09
    èªĵè¨Ģ
    -0.09
    veis
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
     Erotic
    -0.08
    addin
    -0.08
    ừa
    -0.08
    POSITIVE LOGITS
    æı®
    0.09
    -minded
    0.09
    ä¹īåĬ¡
    0.09
    ä¸Ģå¹ħ
    0.08
    svm
    0.08
     minded
    0.08
     Minds
    0.08
    äºĨè§£æĽ´å¤ļ
    0.08
    åĴĮæĬĢæľ¯
    0.08
    ä¸ĵ
    0.07
    Activations Density 0.022%

    No Known Activations