© 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. 58411
    Prev
    Next
    INDEX
    Explanations

    believes

    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
    ä¸ĢäºĮ
    -0.09
    æĪIJäºĨ
    -0.09
    jac
    -0.09
    å±Ģ
    -0.09
     غاÙĦب
    -0.09
    .Parcelable
    -0.09
     Reeves
    -0.08
    tical
    -0.08
     Fortress
    -0.08
    à¸Ĺà¸Ķ
    -0.08
    POSITIVE LOGITS
    æĺ¯æľĢ好çļĦ
    0.11
    ucha
    0.09
    æĺ¯ä¸Ģ件
    0.09
    çĶ¨æĪ·æıIJä¾Ľ
    0.09
    çijķ
    0.08
    PK
    0.08
    èĬĿ
    0.08
     beste
    0.08
    urch
    0.08
    客æĪ·æıIJä¾Ľ
    0.08
    Activations Density 0.085%

    No Known Activations