© 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. 27251
    Prev
    Next
    INDEX
    Explanations

    patent numbers (US)

    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
    ingt
    -0.09
    ingg
    -0.07
    su
    -0.07
    缴è¾ĸ
    -0.07
    _latest
    -0.07
    å¼ķ以为
    -0.06
    æĬĵ
    -0.06
    oko
    -0.06
    ëĭ¹íķľ
    -0.06
     Dustin
    -0.06
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    TypeDef
    0.08
    iers
    0.07
    izzi
    0.07
    пеÑĨ
    0.07
    rh
    0.07
    辩论
    0.07
    fuÃŁ
    0.07
    abas
    0.07
    atz
    0.07
    Activations Density 0.004%

    No Known Activations