© 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. 4443
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and context

    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
    èĴĻå¾·
    -0.07
    DefaultValue
    -0.06
     bas
    -0.06
    é¢ł
    -0.06
    _MON
    -0.06
    é¢łè¦Ĩ
    -0.06
    çIJ³
    -0.06
    éĢĬ
    -0.06
    æĹłä¸Ģ
    -0.06
    çİ°åŃĺ
    -0.06
    POSITIVE LOGITS
    å±ķå¼Ģåħ¨æĸĩ
    0.08
    å§ĭç»Īä¿ĿæĮģ
    0.08
     infi
    0.08
    ä¿ĿæĮģä¸įåıĺ
    0.08
    urz
    0.08
    _relative
    0.07
    eps
    0.07
     scaling
    0.07
    relative
    0.07
     Scaling
    0.07
    Activations Density 0.008%

    No Known Activations