© 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. 50612
    Prev
    Next
    INDEX
    Explanations

    <code>`a ` or `an `</code>

    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
    ULO
    -0.08
    é£ŀåīij
    -0.08
    Scalars
    -0.07
    INU
    -0.07
    /~
    -0.07
    emas
    -0.07
    ÛĮÙĦÛĮ
    -0.07
    ðŁĺī
    -0.07
    esian
    -0.07
    eto
    -0.07
    POSITIVE LOGITS
     infine
    0.07
    راء
    0.07
    æĢ»ä¹ĭ
    0.07
    anza
    0.07
    adic
    0.06
    quÃŃ
    0.06
    令
    0.06
    дÑĸй
    0.06
    æĢ»ä½ĵ
    0.06
    anzas
    0.06
    Activations Density 0.016%

    No Known Activations