© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21604
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constants

    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
    elves
    -0.09
    orang
    -0.08
    å¾·åŁº
    -0.08
    erende
    -0.08
    aces
    -0.08
    ÄĻdzie
    -0.07
    _statistics
    -0.07
    _cpus
    -0.07
    åĪĨ许
    -0.07
    raq
    -0.07
    POSITIVE LOGITS
    çĶ
    0.06
    avec
    0.06
     care
    0.06
    浪
    0.06
    /library
    0.06
     Tér
    0.06
    éĩijçŁ³
    0.06
    åı²
    0.06
    fits
    0.06
    dziel
    0.06
    Activations Density 0.002%

    No Known Activations