© 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. 10552
    Prev
    Next
    INDEX
    Explanations

    leader in

    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
    åĩĿ
    -0.10
    atura
    -0.09
    diamond
    -0.09
    ItemSelected
    -0.09
    秣
    -0.09
    çĩİ
    -0.09
    ä¼ļå½±åĵį
    -0.08
     Alps
    -0.08
    èĸª
    -0.08
    éĴº
    -0.08
    POSITIVE LOGITS
    åľ°ä½į
    0.10
    åIJĮæĹ¶ä¹Łæĺ¯
    0.09
    ä¹ĭä½ľ
    0.09
    åħ¬è®¤çļĦ
    0.08
     миÑĢов
    0.08
    /support
    0.08
    Parms
    0.08
    é¾ļ
    0.08
    æĭįæĭį
    0.08
    称
    0.08
    Activations Density 0.015%

    No Known Activations