© 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. 4411
    Prev
    Next
    INDEX
    Explanations

    affirming

    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
    ä¸įä¿¡
    -0.09
    æ¶Īæŀģ
    -0.09
    pisa
    -0.08
    æĢ»è§īå¾Ĺ
    -0.08
    澧
    -0.08
     liv
    -0.08
    åIJİæĤĶ
    -0.08
     Åģ
    -0.08
    åİĨåı²æĸ°
    -0.08
     Workspace
    -0.08
    POSITIVE LOGITS
    åİŁæľī
    0.12
    çĸ¤
    0.10
    ç»Ŀ大éĥ¨åĪĨ
    0.10
    å¦ĤæľŁ
    0.10
    åİŁæľīçļĦ
    0.10
    æĿĤ
    0.09
     orgy
    0.09
    åİŁ
    0.09
    åĿļå®ļ
    0.09
    æĹ¢æľī
    0.09
    Activations Density 0.038%

    No Known Activations