© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9911
    Prev
    Next
    INDEX
    Explanations

    for

    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
    даÑĢ
    -0.10
    ä½łèĩªå·±
    -0.10
    LIK
    -0.10
    lops
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    æ£ł
    -0.09
    ä¸ĵä¸ļ人士
    -0.09
     поÑĤеÑĢÑı
    -0.09
     обÑıзаÑĤелÑĮно
    -0.09
    åı¦ä¸Ģä½į
    -0.09
    POSITIVE LOGITS
    ÑģÑĭ
    0.08
     being
    0.08
    飬
    0.08
    å¿Ĵ
    0.08
    0.08
    zen
    0.08
    å°¸
    0.08
     using
    0.08
    å°º
    0.08
    çľ¼çķĮ
    0.08
    Activations Density 0.037%

    No Known Activations