© 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. 10010
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    tings
    -0.09
    rede
    -0.09
    åĴĮæĶ¯æĮģ
    -0.08
    åŃIJéĩĮ
    -0.08
    æį¢æĿ¥
    -0.08
    arians
    -0.08
    è¸Į
    -0.08
    uer
    -0.08
    éĤ£ä¸Ģ天
    -0.08
    ughter
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.09
    OfYear
    0.09
    强æľīåĬĽçļĦ
    0.09
    éĿŀ常好çļĦ
    0.08
    APPED
    0.08
    éŀį
    0.08
     steadfast
    0.08
    iry
    0.08
    hest
    0.08
    -dimensional
    0.08
    Activations Density 0.033%

    No Known Activations