© 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. 54048
    Prev
    Next
    INDEX
    Explanations

    app store purchases and ads

    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
    é¢Ī
    -0.10
    atri
    -0.10
    éī´
    -0.09
    ksz
    -0.09
    è°±
    -0.09
    çĥŃæ°´
    -0.09
     Kut
    -0.09
    æĿª
    -0.09
    æ¿Ĵ
    -0.09
    èĦĸåŃIJ
    -0.09
    POSITIVE LOGITS
    æİĮ
    0.09
    gles
    0.09
    è¿Ļ个èģĮä¸ļ
    0.09
    dio
    0.09
    èĨ¨
    0.08
    æ³Ĭ
    0.08
     interviews
    0.08
    èĵĵ
    0.08
    erno
    0.08
    èĤĩ
    0.08
    Activations Density 0.226%

    No Known Activations