© 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. 19041
    Prev
    Next
    INDEX
    Explanations

    Copernicus University and science

    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
     Hav
    -0.09
    æĥ¦
    -0.09
    article
    -0.09
    ä¸įçŁ¥
    -0.08
    zimmer
    -0.08
    enders
    -0.08
    è´ª
    -0.08
    æľĢ大
    -0.08
    ç¬Ħ
    -0.08
    al
    -0.08
    POSITIVE LOGITS
    羣çIJĨ
    0.12
    说æľį
    0.09
    妹åŃIJ
    0.09
    ÙĪÙĤ
    0.09
    æĭ¼
    0.09
    åīįæĻ¯
    0.09
    ç§ijæĬĢè¿ĽæŃ¥
    0.09
     truths
    0.09
    æİĸ
    0.09
    åIJĸ
    0.08
    Activations Density 0.058%

    No Known Activations