© 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. 26426
    Prev
    Next
    INDEX
    Explanations

    This work, article, study, blog, segment

    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
    pls
    -0.10
     Kavanaugh
    -0.08
    lection
    -0.08
    éŃĦ
    -0.08
    æIJŀ
    -0.08
    æł¸æ¡ĥ
    -0.08
    GLOSS
    -0.08
    ä¸Ģä¸ĭåŃIJ
    -0.07
    upert
    -0.07
    Formats
    -0.07
    POSITIVE LOGITS
    æķ´çIJĨ
    0.11
    æĶ¶æĭ¾
    0.10
    æijĺ
    0.09
    äºĨä¸Ģéģį
    0.09
    梳çIJĨ
    0.09
    åIJĦæľī
    0.09
    åħ±åIJĮ
    0.09
     Sek
    0.08
    èįĥ
    0.08
    ran
    0.08
    Activations Density 0.008%

    No Known Activations