© 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. 42140
    Prev
    Next
    INDEX
    Explanations

    markdown and related directives

    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
    chas
    -0.06
    ors
    -0.06
    lop
    -0.06
    asmus
    -0.06
    olicies
    -0.06
    alon
    -0.06
     scel
    -0.06
     Bil
    -0.06
    天åłĤ
    -0.06
     initially
    -0.06
    POSITIVE LOGITS
    pire
    0.08
    arz
    0.08
    idth
    0.08
    ë©ĺ
    0.07
    mist
    0.07
    ä¸Ģèµ·åIJĥ
    0.07
    PFN
    0.07
    缸ç»ĵåIJĪ
    0.07
    uvo
    0.07
     diperc
    0.07
    Activations Density 0.001%

    No Known Activations