© 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. 42959
    Prev
    Next
    INDEX
    Explanations

    logarithms and exponential functions

    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
    çĻ½é¢Ĩ
    -0.07
    å¾ĹåĪ°æľīæķĪ
    -0.07
    çī§
    -0.07
     Futbol
    -0.07
    PCI
    -0.07
     unix
    -0.07
    angelo
    -0.06
    adhan
    -0.06
    _physical
    -0.06
    rin
    -0.06
    POSITIVE LOGITS
    asers
    0.08
     interpol
    0.08
    -log
    0.08
    loge
    0.07
    é»Ħè±Ĩ
    0.07
    unek
    0.07
    ozilla
    0.07
    Powered
    0.07
    é»Ħç´ł
    0.07
    oyer
    0.07
    Activations Density 0.005%

    No Known Activations