© 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. 48194
    Prev
    Next
    INDEX
    Explanations

    phone's activity

    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
    贵宾
    -0.10
     bis
    -0.09
    è¿ĻåĿĹ
    -0.09
    天æ°Ķ
    -0.09
    è´
    -0.09
    é«ĺä»·
    -0.09
    çĽ¥
    -0.08
    .Inner
    -0.08
    迦
    -0.08
    ếm
    -0.08
    POSITIVE LOGITS
    æijĨæĶ¾
    0.11
    éĶIJ
    0.09
    æĶ¾ç½®
    0.09
    dek
    0.08
    -placement
    0.08
     tripod
    0.08
    acements
    0.08
    æ¼ķ
    0.08
    èİ·å¾ĹæĦŁ
    0.08
    æĶ¾åľ¨
    0.08
    Activations Density 0.241%

    No Known Activations