© 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. 43313
    Prev
    Next
    INDEX
    Explanations

    thermodynamics and related physics concepts

    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
     доÑģ
    -0.09
    à¬Ľ
    -0.09
    yscale
    -0.09
    ylon
    -0.09
    ICAST
    -0.08
    \brief
    -0.08
    _perc
    -0.08
    éĶĪ
    -0.08
    inct
    -0.08
    ifest
    -0.08
    POSITIVE LOGITS
     therm
    0.09
     Carn
    0.08
     Therm
    0.08
    çĥŃ
    0.08
    0.08
     fields
    0.07
     vap
    0.07
    çĥŃçļĦ
    0.07
     steam
    0.07
     temperature
    0.07
    Activations Density 0.009%

    No Known Activations