© 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. 37858
    Prev
    Next
    INDEX
    Explanations

    antiquity

    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
    æĸ°çļĦä¸Ģå¹´
    -0.09
    ละ
    -0.09
    ders
    -0.09
    æ¯Ķçī¹
    -0.09
    æľīæĿ¡ä»¶
    -0.09
    ATCH
    -0.08
    AME
    -0.08
    æ»Ĥ
    -0.08
    ulet
    -0.08
    æľīæĿ¡ä»¶çļĦ
    -0.08
    POSITIVE LOGITS
    çİ©æĦı
    0.10
    ties
    0.09
    ãģķãĤī
    0.09
    æħİ
    0.08
    -fashioned
    0.08
    ãģªãĤĬ
    0.08
    佬
    0.08
    çĸĻ
    0.08
    otal
    0.08
    è¯ĥ
    0.08
    Activations Density 0.005%

    No Known Activations