© 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. 45271
    Prev
    Next
    INDEX
    Explanations

    recording activity and usage

    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
    íĮ©
    -0.08
     upfront
    -0.07
    oke
    -0.07
    齿
    -0.07
    aja
    -0.07
    å¸ĪçļĦ
    -0.07
    ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    ç«ŀåĵģä¿¡æģ¯
    -0.07
    åĢ¡
    -0.07
    ARING
    -0.07
    POSITIVE LOGITS
     recorded
    0.11
     activity
    0.11
    é¢ij次
    0.10
    使çĶ¨æĥħåĨµ
    0.10
     Activity
    0.10
    è®°å½ķ
    0.10
     frequency
    0.10
    Activity
    0.09
     frequ
    0.09
    è®°å½ķäºĨ
    0.09
    Activations Density 0.298%

    No Known Activations