© 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. 16957
    Prev
    Next
    INDEX
    Explanations

    former behaviour

    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
    éĻĨç»Ń
    -0.08
    aji
    -0.08
     Katy
    -0.07
     subsequent
    -0.07
    icia
    -0.07
    人为
    -0.07
    çļĦéĩįè¦ģ
    -0.07
    缸继
    -0.07
    -important
    -0.07
    bach
    -0.07
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.17
    èĢĮéĿŀ
    0.16
    æĸ¹å¼ıè¿Ľè¡Į
    0.13
    æĽ´éĢĤåIJĪ
    0.13
     rather
    0.12
    æľĢåIJĪéĢĤ
    0.12
    éĤ£ç§į
    0.12
    rather
    0.12
    åĵªä¸Ģ个
    0.12
    æĽ´èĥ½
    0.11
    Activations Density 0.291%

    No Known Activations