© 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. 25225
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

    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
    ä¹ĭæķ°
    -0.08
     Hals
    -0.07
    åĬ¨è¾Ħ
    -0.07
    ä½łçļĦåIJįåŃĹ
    -0.07
     coste
    -0.07
     casse
    -0.07
    agne
    -0.06
    çĻ»å½ķæŁ¥çľĭ
    -0.06
    åĵŃçĿĢ
    -0.06
    起订
    -0.06
    POSITIVE LOGITS
     fraction
    0.17
    percentage
    0.16
    çĻ¾åĪĨä¹ĭ
    0.16
     percentages
    0.16
    Fraction
    0.16
    fraction
    0.16
     percentage
    0.15
     (%)
    0.15
     Fraction
    0.15
     fractions
    0.15
    Activations Density 0.116%

    No Known Activations