© 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. 28065
    Prev
    Next
    INDEX
    Explanations

    units and ranges

    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
    Ùģت
    -0.09
    edImage
    -0.08
     downstairs
    -0.07
    äºĨåIJĹ
    -0.07
    amac
    -0.07
    antil
    -0.07
    ANNOT
    -0.07
    rasz
    -0.07
     lok
    -0.07
    èIJĮèIJĮ
    -0.07
    POSITIVE LOGITS
     depending
    0.14
    depending
    0.13
     dependendo
    0.11
     tùy
    0.10
    Depending
    0.10
     tuỳ
    0.09
     Depending
    0.09
    åıĸåĨ³äºİ
    0.08
    ãģ®éĸĵ
    0.08
     range
    0.08
    Activations Density 0.139%

    No Known Activations