© 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. 22396
    Prev
    Next
    INDEX
    Explanations

    fractional or divided parts

    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
     prod
    -0.08
    _production
    -0.07
    ConnectionFactory
    -0.07
    ä¸įæ²»
    -0.07
    è§ģè¯Ĩ
    -0.07
    ìĩĦ
    -0.07
    _prod
    -0.07
     Rim
    -0.06
    ä¿Ŀ
    -0.06
     press
    -0.06
    POSITIVE LOGITS
     fractional
    0.12
     interpolated
    0.11
     fractions
    0.11
    精确
    0.10
     interpolation
    0.10
    ä»ĭäºİ
    0.10
     interpol
    0.10
     interpolate
    0.09
    æıĴ
    0.09
     fraction
    0.09
    Activations Density 0.036%

    No Known Activations