© 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. 31146
    Prev
    Next
    INDEX
    Explanations

    risk of developing

    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
    åĸ»
    -0.11
    _caps
    -0.08
    utable
    -0.08
    æłī
    -0.08
     trò
    -0.08
    åįĬ天
    -0.08
    Tpl
    -0.08
    ornings
    -0.08
    queda
    -0.08
    æĬ¿
    -0.08
    POSITIVE LOGITS
    èĨĽ
    0.10
    å¿ĥåĬ¨
    0.09
    awi
    0.09
    ãģŁãģı
    0.09
    ä½ķåĨµ
    0.09
    æĸ°çļĦ
    0.09
    æĪĸå°Ĩ
    0.08
    æĥħåĨµè¿Ľè¡Į
    0.08
    æīĪ
    0.08
    ä¸įäºĨ
    0.08
    Activations Density 0.069%

    No Known Activations