© 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. 32674
    Prev
    Next
    INDEX
    Explanations

    main goal or objective

    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
    åħ·ä½ĵåĨħ容
    -0.11
    æĽ´å¥½
    -0.11
    æľīä¸Ģå®ļ
    -0.10
    è±ī
    -0.09
    ÙĪÙĬد
    -0.09
    tsy
    -0.09
    obel
    -0.09
    åħ·ä½ĵæĥħåĨµ
    -0.09
    ennen
    -0.09
     cụ
    -0.09
    POSITIVE LOGITS
    åĬĽè¿ĺæĺ¯
    0.10
    è¿ĺæĺ¯è¦ģ
    0.10
    èī²è°ĥ
    0.10
    ä¹ĭä¸Ģ
    0.09
    imum
    0.09
    stay
    0.09
    mah
    0.09
    两大
    0.08
    loor
    0.08
    AxisSize
    0.08
    Activations Density 0.333%

    No Known Activations