© 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. 33983
    Prev
    Next
    INDEX
    Explanations

    logistical information, base, technically featured

    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
    ç½°
    -0.09
    ç½ļ
    -0.09
     Fashion
    -0.08
    åħī线
    -0.08
    æħİ
    -0.08
    è¿Ļ份
    -0.08
    mins
    -0.08
     Hermes
    -0.08
    IFT
    -0.08
    ooky
    -0.08
    POSITIVE LOGITS
    æľ´å®ŀ
    0.10
    å¸ı
    0.10
    owell
    0.09
    ä¼Ļ
    0.09
    士
    0.09
    èIJ¥åľ°
    0.09
    帷
    0.09
    æį¢
    0.09
    èĪ
    0.09
    åĻ¨æĿIJ
    0.09
    Activations Density 0.125%

    No Known Activations