© 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. 22563
    Prev
    Next
    INDEX
    Explanations

    numerical computations or programming constructs

    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
    gor
    -0.07
    van
    -0.07
    rait
    -0.06
    {text
    -0.06
    为çĶ±
    -0.06
     Pett
    -0.06
     Bros
    -0.06
    âĢ¦
    -0.06
    CTR
    -0.06
     stripping
    -0.06
    POSITIVE LOGITS
    ×ķ×Ŀ
    0.08
    bsolute
    0.08
    ç©
    0.08
     dituj
    0.08
     diranc
    0.08
    HeaderValue
    0.07
    imson
    0.07
    .numpy
    0.07
    getClass
    0.07
     VÃŃc
    0.07
    Activations Density 0.001%

    No Known Activations