© 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. 27616
    Prev
    Next
    INDEX
    Explanations

    range between min and max

    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
    roj
    -0.09
     ÑģеÑĢеб
    -0.08
    зал
    -0.08
     Erot
    -0.08
    éĻ©
    -0.08
    γÏīγ
    -0.08
    é¾Ħ
    -0.08
    ONS
    -0.08
    纽
    -0.08
    ++.
    -0.08
    POSITIVE LOGITS
     ranges
    0.09
     range
    0.09
     ranging
    0.09
    èĮĥåĽ´ä¸º
    0.09
     Range
    0.08
    èĮĥåĽ´
    0.08
    çļĦèĮĥåĽ´
    0.08
    é¸ŃèĽĭ
    0.07
    alue
    0.07
     values
    0.07
    Activations Density 0.044%

    No Known Activations