© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    issue tracker

    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
    æŦ
    -0.09
    è¯ķçĤ¹
    -0.09
    çľĭä¸Ĭåİ»
    -0.09
    俯
    -0.09
    æݨ广
    -0.09
    çļĦæĥħ绪
    -0.09
    _retry
    -0.09
    é£ŀè¡Įåijĺ
    -0.08
    çĬ¬
    -0.08
    ä¸İä¼Ĺ
    -0.08
    POSITIVE LOGITS
     ticket
    0.11
     tickets
    0.10
     билеÑĤ
    0.10
    -ticket
    0.10
     Tickets
    0.10
    bug
    0.09
    æĢª
    0.09
    ticket
    0.09
    交
    0.09
    票
    0.09
    Activations Density 0.129%

    No Known Activations