© 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. 40158
    Prev
    Next
    INDEX
    Explanations

    thermal equilibrium state

    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
    à¹Īà¸Ļ
    -0.09
    nop
    -0.08
    aphrag
    -0.07
    enov
    -0.07
    itto
    -0.07
    jó
    -0.07
    uyen
    -0.07
     tóm
    -0.07
    á»ķ
    -0.07
    å¾ŀæѤ
    -0.07
    POSITIVE LOGITS
    -state
    0.07
     internally
    0.07
    -ish
    0.07
    æ¿®
    0.07
    -like
    0.06
    hot
    0.06
     state
    0.06
     locally
    0.06
     Bose
    0.06
    çĬ¶æĢģä¸ĭ
    0.06
    Activations Density 0.007%

    No Known Activations