© 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. 58063
    Prev
    Next
    INDEX
    Explanations

    umbrella

    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
    åľ°éģĵ
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
     Belt
    -0.09
    æĿŁ
    -0.09
     demographics
    -0.09
    æĬĬæı¡
    -0.09
    lotte
    -0.08
    éĥijéĩį
    -0.08
     dip
    -0.08
    _DETAIL
    -0.08
    POSITIVE LOGITS
    ä¼ŀ
    0.16
     umbrella
    0.14
     shelter
    0.10
    笳
    0.10
     umb
    0.10
    æĴij
    0.10
     Umb
    0.10
    篷
    0.10
    éĺ²æĻĴ
    0.10
    äºŃ
    0.09
    Activations Density 0.052%

    No Known Activations