© 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. 40296
    Prev
    Next
    INDEX
    Explanations

    emissivity

    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
    edos
    -0.07
     unserialize
    -0.07
    μÏĨ
    -0.07
     Offline
    -0.07
    apult
    -0.07
    Offline
    -0.07
     offline
    -0.07
    ì§ķ
    -0.06
     ÙĦÙĦبÙĨ
    -0.06
    arkt
    -0.06
    POSITIVE LOGITS
     thermal
    0.11
     mutually
    0.11
     emiss
    0.10
    thermal
    0.10
     Thermal
    0.09
    รà¹īà¸Ńà¸Ļ
    0.08
    缸äºĴ
    0.08
     mutual
    0.08
    çĥŃæºIJ
    0.08
     recip
    0.08
    Activations Density 0.003%

    No Known Activations