© 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. 33325
    Prev
    Next
    INDEX
    Explanations

    http links and browsing

    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
    çĦ¶æĺ¯
    -0.13
     Cater
    -0.09
    /OR
    -0.09
    ients
    -0.08
     Orr
    -0.08
    笳
    -0.08
     Exhibit
    -0.08
     contr
    -0.08
    æľī趣çļĦ
    -0.08
    æģ°æģ°
    -0.08
    POSITIVE LOGITS
    _EPS
    0.08
    äºİæĺ¯
    0.08
    ä¼ģä¸ļæıIJä¾Ľ
    0.08
    åįĥæĸ¹çĻ¾è®¡
    0.08
    oms
    0.08
    ès
    0.08
    unky
    0.08
    æĢ¨
    0.08
    ical
    0.08
    eral
    0.08
    Activations Density 0.214%

    No Known Activations