© 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. 57915
    Prev
    Next
    INDEX
    Explanations

    head of

    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
    |#
    -0.10
    sap
    -0.09
    ãģ°ãģĭãĤĬ
    -0.08
     Fern
    -0.08
    allen
    -0.08
    PropertyDescriptor
    -0.08
    è¡Į车
    -0.08
    orf
    -0.08
    ç©Ĺ
    -0.08
    è·Į
    -0.08
    POSITIVE LOGITS
    丰满
    0.10
    大éĿ¢ç§¯
    0.09
    UTES
    0.09
    è¿IJä½ľ
    0.09
    åºŀ大çļĦ
    0.09
    æĺı
    0.09
    æľīåħ³éĥ¨éŨ
    0.08
     deg
    0.08
    å®īä¿Ŀ
    0.08
    åºŀ大
    0.08
    Activations Density 0.022%

    No Known Activations