© 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. 4687
    Prev
    Next
    INDEX
    Explanations

    abounding, galore, apace

    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
    æ·ŀ
    -0.10
    ä¸įå¾Ĺä¸į说
    -0.10
    ä¸ĢåĽŀäºĭ
    -0.10
    à¹Į
    -0.10
    赶ä¸Ĭ
    -0.10
    é«Ĥ
    -0.09
    å·®çĤ¹
    -0.09
    ourke
    -0.09
    AMED
    -0.08
    Inlining
    -0.08
    POSITIVE LOGITS
     Herc
    0.08
    åįķåĵģ
    0.08
     sia
    0.08
    ìĶ¬
    0.08
    ercial
    0.08
    .setVertical
    0.08
    ean
    0.08
    ضرب
    0.08
    ey
    0.08
    erior
    0.08
    Activations Density 0.012%

    No Known Activations