© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19941
    Prev
    Next
    INDEX
    Explanations

    Austin or Auburn

    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
    èºģ
    -0.11
    ı
    -0.10
    owski
    -0.10
    ëĭ¥
    -0.09
     dụ
    -0.09
    æı¿
    -0.09
    ä¸ĭ车
    -0.09
    gings
    -0.09
    累累
    -0.09
    æĭĹ
    -0.09
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.11
    -going
    0.09
    æ¼ĵ
    0.09
    .writeValue
    0.08
    à¹Į
    0.08
    imum
    0.08
    tra
    0.08
    empor
    0.08
    imal
    0.08
    eing
    0.08
    Activations Density 0.011%

    No Known Activations