© 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. 42076
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
     dire
    -0.06
    çªģåĩ»
    -0.06
     ê°
    -0.06
    å§ĭèĩ³ç»Ī
    -0.06
    串
    -0.06
     derived
    -0.06
    å®ŀè´¨
    -0.06
    æŀģ
    -0.06
    åİķ
    -0.06
    åħ¬å¹³
    -0.05
    POSITIVE LOGITS
    aine
    0.08
    outil
    0.08
    anjung
    0.08
    µ¬
    0.08
    lea
    0.07
    _Parse
    0.07
    UILTIN
    0.07
    sworth
    0.07
    %D
    0.07
     Duy
    0.07
    Activations Density 0.008%

    No Known Activations