© 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. 23304
    Prev
    Next
    INDEX
    Explanations

    claims priority from Korean Patent

    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
    çīĮåŃIJ
    -0.09
    çĶļèĩ³æĺ¯
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
    ä¸Ŀ绸
    -0.08
    ipse
    -0.08
     coz
    -0.08
    дÑĥ
    -0.08
     themselves
    -0.08
     follower
    -0.08
    æĭ±
    -0.08
    POSITIVE LOGITS
    sert
    0.10
    /ubuntu
    0.09
    rides
    0.09
    CAPE
    0.08
    è¾Ķ
    0.08
    åIJŀ
    0.08
    ä½ıåľ¨
    0.08
    Ñĭми
    0.08
    vertise
    0.08
    .ShowDialog
    0.08
    Activations Density 0.004%

    No Known Activations