© 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. 63817
    Prev
    Next
    INDEX
    Explanations

    length scale and relaxation time

    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
     borderBottom
    -0.08
    (te
    -0.08
    乡亲们
    -0.07
    åŀ£
    -0.07
    豺
    -0.07
    åıĹä»ĺ
    -0.07
    ¹
    -0.07
     spol
    -0.07
    rio
    -0.07
    HANDLE
    -0.07
    POSITIVE LOGITS
    abda
    0.08
    æ³Į
    0.07
    unker
    0.07
     concentr
    0.07
    Equals
    0.07
     kern
    0.06
    å¹²
    0.06
    ebro
    0.06
    arth
    0.06
    ä¸İå®ŀéĻħ
    0.06
    Activations Density 0.004%

    No Known Activations