© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37641
    Prev
    Next
    INDEX
    Explanations

    cost and price inquiries

    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
    à¹ģà¸Ī
    -0.09
    agma
    -0.09
    积
    -0.09
    _pg
    -0.09
    æľªæĪIJ
    -0.09
    åı¯æĥľ
    -0.09
    æĮ£
    -0.09
    UNCH
    -0.08
    icum
    -0.08
     sug
    -0.08
    POSITIVE LOGITS
    代价
    0.13
    æĪIJæľ¬
    0.10
    é«ĺæĺĤ
    0.10
    太é«ĺ
    0.10
    åIJİæŀľ
    0.09
    æĻ¯å¾·
    0.09
    æĺĤè´µ
    0.09
    è´Łæĭħ
    0.09
    çĪµ
    0.09
    .metro
    0.09
    Activations Density 0.074%

    No Known Activations