© 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. 29376
    Prev
    Next
    INDEX
    Explanations

    scaling, simple, optimal

    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
    鸳
    -0.09
    _PLATFORM
    -0.08
    aky
    -0.08
    igl
    -0.07
    _sdk
    -0.07
     naw
    -0.07
    atti
    -0.07
    anat
    -0.07
    à¸Ŀ
    -0.07
    platform
    -0.07
    POSITIVE LOGITS
     homogeneous
    0.10
     uniform
    0.10
     simpl
    0.10
     linear
    0.09
     simplify
    0.09
     predictable
    0.09
    ç®ĢåĮĸ
    0.09
    线æĢ§
    0.08
     одноÑĢод
    0.08
     simplific
    0.08
    Activations Density 0.065%

    No Known Activations