© 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. 26596
    Prev
    Next
    INDEX
    Explanations

    Sports, Travel, Trade, Tech

    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
    ipse
    -0.09
    ή
    -0.08
    itan
    -0.08
    avigator
    -0.08
    olen
    -0.08
     Malone
    -0.08
    oons
    -0.08
    /member
    -0.08
    istra
    -0.08
     pur
    -0.07
    POSITIVE LOGITS
    æĺ¯åĽ½åĨħ
    0.10
    èļģ
    0.10
    PMC
    0.09
    ä½łä¸į
    0.09
     nét
    0.09
    æľ¬è½®
    0.09
    æ¯ı次éĥ½
    0.09
    pollo
    0.09
    _finalize
    0.09
    ison
    0.09
    Activations Density 0.003%

    No Known Activations