© 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. 48110
    Prev
    Next
    INDEX
    Explanations

    designated as precedent

    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
    alyze
    -0.09
    лиÑģÑĤ
    -0.09
     Sp
    -0.09
    Sp
    -0.08
    y
    -0.08
    orate
    -0.08
    åłĥ
    -0.08
    eat
    -0.08
    /MIT
    -0.08
    illard
    -0.08
    POSITIVE LOGITS
    åĪģ
    0.10
    å®¡æł¸
    0.09
    ãĥķãĤ¡ãĥ¼
    0.09
    磮
    0.09
    æľīæĦı
    0.09
    è®°å¾Ĺ
    0.09
    æĬ¥ä»·
    0.09
    ç¼®
    0.09
    æģĤ
    0.09
    èł¡
    0.09
    Activations Density 0.002%

    No Known Activations