© 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. 3149
    Prev
    Next
    INDEX
    Explanations

    under one or more

    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
     Bingo
    -0.09
    åĽŀæĿ¥äºĨ
    -0.08
    istik
    -0.08
    çħĬ
    -0.08
    prech
    -0.08
    peg
    -0.08
    ç½ij讯
    -0.07
    åĮ»ç§ij
    -0.07
    æ´¥
    -0.07
    åĨĮ
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.10
    å·¥ä½ľä¸Ń
    0.10
    åı£ä¸Ń
    0.09
    ONSE
    0.09
    ä½ķåĨµ
    0.09
    派驻
    0.09
    èĦIJ
    0.09
    æĹĹä¸ĭ
    0.09
     Sims
    0.09
     Mog
    0.08
    Activations Density 2.198%

    No Known Activations