© 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. 47626
    Prev
    Next
    INDEX
    Explanations

    digital media content

    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
    æĪijçļĦç¥Ŀç¦ı
    -0.08
    )":
    -0.07
    ottle
    -0.07
    odos
    -0.07
    chaffen
    -0.07
    iage
    -0.07
    zure
    -0.07
    .codes
    -0.07
    ä¸į代表
    -0.07
    Äįen
    -0.07
    POSITIVE LOGITS
    缸åºĶçļĦ
    0.07
    欢è¿İæĤ¨
    0.07
    æ¼±
    0.07
    该åĨħ容
    0.06
     held
    0.06
    æĮģ
    0.06
     Ñģбо
    0.06
    elter
    0.06
     whose
    0.06
    çļĦå®ŀéĻħ
    0.06
    Activations Density 0.098%

    No Known Activations