© 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. 55498
    Prev
    Next
    INDEX
    Explanations

    scale measurements

    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
    isy
    -0.07
    æŃĮ声
    -0.06
    åıłåĬł
    -0.06
     Conce
    -0.06
    anked
    -0.06
    alis
    -0.06
    _HEADERS
    -0.06
    link
    -0.06
    antal
    -0.06
    antino
    -0.06
    POSITIVE LOGITS
    尺度
    0.09
     scale
    0.09
     scales
    0.09
     scaling
    0.09
     Scale
    0.09
    ä¸īå°º
    0.08
    å°º
    0.08
    æıIJä¾ĽåıĤèĢĥ
    0.08
    scale
    0.08
    reference
    0.08
    Activations Density 0.008%

    No Known Activations