© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13977
    Prev
    Next
    INDEX
    Explanations

    initialization code or specific identifiers

    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
    afil
    -0.07
    主è¦ģ为
    -0.06
     Nog
    -0.06
     general
    -0.06
    oooooooo
    -0.06
    以åıĬ对
    -0.06
    ilo
    -0.06
    ãģŁãģŁ
    -0.06
    general
    -0.06
    ä¸Ńåįİæ°ijæĹıçļĦ
    -0.06
    POSITIVE LOGITS
    poon
    0.08
    ÙĬاء
    0.08
    urig
    0.07
    åĩłçĤ¹
    0.07
    libs
    0.07
    lÃł
    0.07
    Würt
    0.07
    æĿ¥æĦĪ
    0.07
    åİŁä»¶
    0.07
    ewan
    0.07
    Activations Density 0.050%

    No Known Activations