© 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. 20010
    Prev
    Next
    INDEX
    Explanations

    fractions or proportions involving three

    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
    ìĮį
    -0.08
    abaya
    -0.08
    astica
    -0.08
    WithType
    -0.08
    ä¸ĢæľĽ
    -0.08
    unica
    -0.08
    èĭ¥å¹²éĹ®é¢ĺçļĦ解éĩĬ
    -0.07
    IFEST
    -0.07
    ä¹İä¹İçļĦ
    -0.07
    ipment
    -0.07
    POSITIVE LOGITS
    ament
    0.08
    º
    0.07
    豺
    0.07
    elu
    0.07
    istr
    0.07
    rd
    0.06
    ajari
    0.06
    irk
    0.06
    åĬłå¼ºåŃ¦ä¹ł
    0.06
    ga
    0.06
    Activations Density 0.014%

    No Known Activations