© 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. 60841
    Prev
    Next
    INDEX
    Explanations

    numbers or variables with operators

    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
    æĤį
    -0.08
    ók
    -0.08
    allen
    -0.08
    ç»ıå¾Ĺèµ·
    -0.07
    allon
    -0.07
    ooth
    -0.07
    第ä¸Ģåľº
    -0.07
     approximate
    -0.07
    à°Ĥà°¦
    -0.07
     Tóm
    -0.07
    POSITIVE LOGITS
    utsch
    0.07
    ä¸ĢæıIJ
    0.07
     added
    0.07
     Muda
    0.07
    less
    0.06
    ictured
    0.06
    åĴĮå¹³
    0.06
    èı©æıIJ
    0.06
    åĨįèµ·
    0.06
    ç¿»
    0.06
    Activations Density 0.017%

    No Known Activations