© 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. 24435
    Prev
    Next
    INDEX
    Explanations

    units and symbols

    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
    inni
    -0.07
    WithContext
    -0.07
    :/
    -0.07
    untung
    -0.07
    ieres
    -0.07
    OutOf
    -0.07
    ossi
    -0.07
    skem
    -0.07
    人æīĭ
    -0.07
    ndl
    -0.07
    POSITIVE LOGITS
    íĻĶ
    0.07
    ä¹ħ
    0.07
     invaders
    0.07
    Æ°á»Ľ
    0.07
    rab
    0.07
     fav
    0.07
    riture
    0.07
    raj
    0.06
    над
    0.06
    fam
    0.06
    Activations Density 0.002%

    No Known Activations