© 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. 61357
    Prev
    Next
    INDEX
    Explanations

    with

    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
    ä¸į该
    -0.10
    empor
    -0.10
    å¸Ŀ
    -0.09
    ixa
    -0.09
    ä¸įä»ħ
    -0.09
    为客æĪ·
    -0.09
    渴
    -0.09
    为æѤ
    -0.09
    å®ŀéĻħä¸Ĭæĺ¯
    -0.08
    èĩªæѤ
    -0.08
    POSITIVE LOGITS
    inate
    0.10
    unately
    0.09
    é«ĺ涨
    0.09
    å¾Ĺä¸įåĪ°
    0.09
    æ¯ı天éĥ½
    0.09
    ä¸Ģç§Ĵ
    0.09
    ä¸įåĪ°
    0.09
     luck
    0.08
    缺ä¹ı
    0.08
    åħ¥éŨ
    0.08
    Activations Density 0.050%

    No Known Activations