© 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. 56047
    Prev
    Next
    INDEX
    Explanations

    known from practice

    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
    à¸ļรร
    -0.11
     uninitialized
    -0.10
    åĴĮåľ°åĮº
    -0.09
    åĭŁèµĦ
    -0.09
    æĿĸ
    -0.09
    AndWait
    -0.09
    æıª
    -0.08
    å±ķåĩº
    -0.08
    çµ®
    -0.08
    obo
    -0.08
    POSITIVE LOGITS
    æĿ¥èĩª
    0.15
    à¸Īาà¸ģà¸ģาร
    0.12
     from
    0.12
    ä¾Ĩèĩª
    0.12
    ãģĭãĤīãģ®
    0.11
     từ
    0.11
    (previous
    0.11
    æĿ¥èĩªäºİ
    0.11
    à¸Īาà¸ģ
    0.11
    previous
    0.11
    Activations Density 0.156%

    No Known Activations