© 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. 24934
    Prev
    Next
    INDEX
    Explanations

    domain names and URLs

    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
    olio
    -0.08
    ,default
    -0.08
    groupName
    -0.08
    好åIJĹ
    -0.07
    大水
    -0.07
    =sub
    -0.07
    ÙĤÙĬب
    -0.07
    azzino
    -0.07
    ahal
    -0.07
    åĨħ容ç®Ģä»ĭ
    -0.07
    POSITIVE LOGITS
    _utilities
    0.06
    äºijå³°
    0.06
    ä¿®æ³ķ
    0.06
    ighton
    0.06
     enlightened
    0.06
    ocities
    0.06
    ä¾£
    0.06
     empir
    0.06
     spreadsheet
    0.06
    å·¡åĽŀ
    0.06
    Activations Density 0.536%

    No Known Activations