© 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. 32363
    Prev
    Next
    INDEX
    Explanations

    average, averaging, shared

    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
     Plenty
    -0.08
    teria
    -0.08
    ä¹ħè¿Ŀ
    -0.08
    达产年
    -0.08
    .Failure
    -0.07
    äºĶè°·
    -0.07
    GOR
    -0.07
    ר×Ĵ
    -0.07
    upati
    -0.07
    istan
    -0.07
    POSITIVE LOGITS
     averaging
    0.08
    èŀįåIJĪ
    0.08
     averaged
    0.07
    åĪĨä¸įæ¸ħ
    0.07
    blend
    0.07
    èĿ
    0.07
     binding
    0.07
     distributing
    0.07
    Uniform
    0.07
    模ç³Ĭ
    0.07
    Activations Density 0.003%

    No Known Activations