© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 58077
    Prev
    Next
    INDEX
    Explanations

    over time

    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
    åIJĪãĤıãģĽ
    -0.10
    æĹ¥å¸¸å·¥ä½ľ
    -0.10
    /inc
    -0.10
    ä½Ŀ
    -0.10
    ä»Ĭ
    -0.09
    åݻ年åIJĮæľŁ
    -0.09
    æĹ©æĹ©
    -0.09
    acen
    -0.09
    acks
    -0.09
    çİ°åľ¨å·²ç»ı
    -0.09
    POSITIVE LOGITS
    æĪIJ为ä¸Ģ个
    0.09
    工夫
    0.09
    大å¸Ī
    0.08
    lass
    0.08
    ascript
    0.08
    _notice
    0.08
    è¿Ļå¥Ĺ
    0.08
    çļĦæĹ¶éĹ´éĩĮ
    0.08
    æĪIJ为
    0.08
    otechn
    0.07
    Activations Density 0.015%

    No Known Activations