© 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. 18500
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
    (gp
    -0.09
    جار
    -0.09
    Composition
    -0.08
    éĢIJå¹´
    -0.08
    éģĵçIJĨ
    -0.08
    æ¶Ī
    -0.08
    ä¼ĺåħĪ
    -0.08
    ä¸īä½įä¸Ģä½ĵ
    -0.08
    tml
    -0.08
    entin
    -0.08
    POSITIVE LOGITS
    çļĦæľĢåIJİä¸Ģ
    0.12
    第
    0.11
    第åįģ
    0.11
    第ä¸ī个
    0.10
    累积
    0.10
    éĽķ
    0.10
    第ä¸ĢçĻ¾
    0.09
    累计
    0.09
    æľĢåIJİä¸Ģ个
    0.09
    æĢģ
    0.09
    Activations Density 0.073%

    No Known Activations