© 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. 34047
    Prev
    Next
    INDEX
    Explanations

    mathematics and science notation

    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
    ibase
    -0.08
    resa
    -0.07
    /Base
    -0.07
    鸥
    -0.07
    éĶ¡
    -0.07
     Max
    -0.07
    isie
    -0.07
    atten
    -0.07
    andra
    -0.06
    Ñĥго
    -0.06
    POSITIVE LOGITS
     intervals
    0.09
    angelog
    0.08
    çļĦåħ³éĶ®æĹ¶æľŁ
    0.08
     INTERVAL
    0.08
     Interval
    0.08
    åĽ´
    0.07
     пÑĢоме
    0.07
     regions
    0.07
    Interval
    0.07
     Shiv
    0.07
    Activations Density 0.002%

    No Known Activations