© 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. 33932
    Prev
    Next
    INDEX
    Explanations

    version numbers and punctuation

    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
    /stretch
    -0.07
    ukum
    -0.07
     Patr
    -0.07
    èµ·èĪŀ
    -0.06
    ä¸Ń寻æī¾
    -0.06
    itif
    -0.06
    udas
    -0.06
    /Branch
    -0.06
    alink
    -0.06
    åį°
    -0.06
    POSITIVE LOGITS
    åĮºåĪĨ
    0.08
    ä¸ĭåIJĮ
    0.08
    å®ĮåĸĦ
    0.07
    以æĿ¥çļĦ
    0.07
    æĶ¹
    0.07
     refined
    0.07
    beg
    0.07
    ä¸įå°½
    0.06
     onwards
    0.06
     refinement
    0.06
    Activations Density 0.193%

    No Known Activations