© 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. 30792
    Prev
    Next
    INDEX
    Explanations

    resource or information

    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
    çĶµå½±éĻ¢
    -0.09
    ä½Ĩä¸įéĻIJ
    -0.09
    为æĬĵ
    -0.09
    ä¹ŁçŁ¥éģĵ
    -0.09
    åĪ
    -0.09
    以èī²
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    桧
    -0.08
    çļĦæĥħåĨµä¸ĭ
    -0.08
    çļĦåİĭåĬĽ
    -0.08
    POSITIVE LOGITS
    hana
    0.09
     Donne
    0.08
    .LA
    0.08
    ç©·
    0.08
    天æĸĩ
    0.08
     dw
    0.08
    amedi
    0.08
    éĥģ
    0.08
    idata
    0.08
    涯
    0.08
    Activations Density 0.031%

    No Known Activations