© 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. 47345
    Prev
    Next
    INDEX
    Explanations

    comparison terms and quantities

    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
    ÑĤÑĮе
    -0.09
    ril
    -0.08
    .tie
    -0.07
    á»ħm
    -0.07
     именно
    -0.07
    ourse
    -0.07
    ters
    -0.07
     Wies
    -0.07
    ukum
    -0.07
     precisely
    -0.07
    POSITIVE LOGITS
     than
    0.09
    äºĨä¸ĢåįĬ
    0.08
    ä¹İ
    0.08
     halfway
    0.08
    lina
    0.08
    ysi
    0.07
     kuin
    0.07
     half
    0.07
    ielle
    0.07
    临çķĮ
    0.07
    Activations Density 0.143%

    No Known Activations