© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    version of

    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
    anner
    -0.09
    ssc
    -0.08
    oun
    -0.08
    azen
    -0.08
     Blob
    -0.08
    å¾®åķĨ
    -0.08
    è£Ŀ
    -0.08
    ãĤŃãĥ³
    -0.08
    åıĪ好
    -0.08
    å¤¸å¼ł
    -0.08
    POSITIVE LOGITS
    åĬ¨äºº
    0.11
    å·²ç»ıæľīäºĨ
    0.10
    äºĨä¸Ģéģį
    0.10
    æĥħåĨµè¿Ľè¡Į
    0.10
    lasses
    0.10
    èĢģ人家
    0.10
    å¾ĹæĦı
    0.10
    warts
    0.09
    磨
    0.09
    æĺĶæĹ¥
    0.09
    Activations Density 0.241%

    No Known Activations