© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13659
    Prev
    Next
    INDEX
    Explanations

    suited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ£å¸¸ä½¿çĶ¨
    -0.07
    为确ä¿Ŀ
    -0.07
    çļĦæĦıæĢĿ
    -0.07
    大åĪ°
    -0.07
    dge
    -0.07
    atii
    -0.06
    æŃ£å¸¸æĥħåĨµä¸ĭ
    -0.06
    å°½åı¯èĥ½
    -0.06
     conditioned
    -0.06
    为äºĨä¸į
    -0.06
    POSITIVE LOGITS
    å¾ĪéĢĤåIJĪ
    0.15
    éĿŀ常éĢĤåIJĪ
    0.14
    å¥ijåIJĪ
    0.14
    æľĢéĢĤåIJĪ
    0.13
    æ¯Ķè¾ĥéĢĤåIJĪ
    0.13
    æĽ´éĢĤåIJĪ
    0.13
     suited
    0.13
    éĢĤåIJĪçļĦ
    0.12
    éĢĤåIJĪ
    0.12
    çī¹åĪ«éĢĤåIJĪ
    0.11
    Activations Density 0.097%

    No Known Activations