© 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. 26660
    Prev
    Next
    INDEX
    Explanations

    approximate / approximately

    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
    áĢ·
    -0.10
    ième
    -0.10
    astra
    -0.09
    antine
    -0.09
    /her
    -0.09
    alet
    -0.09
    ample
    -0.09
    monton
    -0.09
    gable
    -0.09
    peÄį
    -0.09
    POSITIVE LOGITS
    LY
    0.08
    imations
    0.07
    imating
    0.07
    Ñıд
    0.07
    (
    0.06
    ities
    0.06
    ,
    0.06
    å¢ħ
    0.06
    mente
    0.06
     اÛĮÙĨÚ©Ùĩ
    0.06
    Activations Density 0.010%

    No Known Activations