© 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. 34378
    Prev
    Next
    INDEX
    Explanations

    topics and subject matter

    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
    æĿ¥åģļ
    -0.09
    itaire
    -0.09
    plain
    -0.09
    æIJŀå¾Ĺ
    -0.09
    太å¤ļçļĦ
    -0.08
    /Foundation
    -0.08
    æīİ
    -0.08
    eli
    -0.08
    æĺ¯å¤ļå°ij
    -0.08
    _OC
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåı«
    0.10
    çŃij
    0.09
    çļĦå°±æĺ¯
    0.09
    èĵŁ
    0.09
    çŃīåIJĦç§į
    0.09
     why
    0.09
     various
    0.08
    çīĴ
    0.08
    端æŃ£
    0.08
    å½¹
    0.08
    Activations Density 0.053%

    No Known Activations