© 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. 42095
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    UpdatedAt
    -0.07
    arno
    -0.07
    ntag
    -0.07
    idin
    -0.06
     wherever
    -0.06
    å¹²åĬ²
    -0.06
    å°Ĩè¿İæĿ¥
    -0.06
    ب
    -0.06
    çļĦåħ¶ä»ĸ
    -0.06
     tiada
    -0.06
    POSITIVE LOGITS
    �t
    0.07
    交æĺĵä¼ļ
    0.07
    éķ·å¤§
    0.07
    .BAD
    0.07
    ţ
    0.06
    éĿĴ天
    0.06
    sez
    0.06
    ùi
    0.06
    rapper
    0.06
    åĴĮèī¯å¥½çļĦ
    0.06
    Activations Density 0.022%

    No Known Activations