© 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. 19038
    Prev
    Next
    INDEX
    Explanations

    temperature dependence

    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
    å¢ħ
    -0.06
    fans
    -0.06
    powered
    -0.06
    èĦijçŃĭ
    -0.06
    ilon
    -0.06
    .stringify
    -0.06
    oom
    -0.06
     outs
    -0.06
     Sund
    -0.06
    enez
    -0.06
    POSITIVE LOGITS
    aggio
    0.08
    aggi
    0.08
    温度åĴĮ
    0.08
     temperatur
    0.07
    yme
    0.07
    ä¸ĭè°ĥ
    0.07
    .FileSystem
    0.07
    edel
    0.07
     Procedures
    0.07
     courant
    0.07
    Activations Density 0.002%

    No Known Activations