© 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. 50309
    Prev
    Next
    INDEX
    Explanations

    sopranino, soprano, SOPHOMORE, Sophus, Shropshire

    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
    漪
    -0.11
    å¸Ŀ
    -0.11
    åħ¬çĽĬæĢ§
    -0.11
    åĪ©çĶ¨çİĩ
    -0.10
    èĴº
    -0.09
    éĢĨè¡Į
    -0.09
    cale
    -0.09
    æѤåĪ»
    -0.09
    ç¥
    -0.09
    OrCreate
    -0.09
    POSITIVE LOGITS
    ../../../
    0.10
    reen
    0.09
    ä¸įä½ı
    0.09
    ton
    0.09
    æĻļæĬ¥
    0.09
    åijĺ
    0.08
    ftware
    0.08
    reme
    0.08
    edio
    0.08
    al
    0.08
    Activations Density 0.004%

    No Known Activations