© 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. 26023
    Prev
    Next
    INDEX
    Explanations

    developing new programs or projects

    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
     Tore
    -0.06
    åĻ¢
    -0.06
    astes
    -0.05
     stun
    -0.05
    AYS
    -0.05
    urras
    -0.05
     Aad
    -0.05
    åĪ«æł·çļĦ
    -0.05
    (Main
    -0.05
    _MPI
    -0.05
    POSITIVE LOGITS
    ä¸Ĭè¿°äºĭå®ŀ
    0.08
    åīįè¿°
    0.08
    _IGNORE
    0.08
    çľ¼èĬ±
    0.08
    ông
    0.08
    æĺİç¡®æĮĩåĩº
    0.07
    ãģĵãģĿ
    0.07
    æ³½
    0.07
    æĹ¥å®£å¸ĥ
    0.07
     모ë¦Ħ
    0.07
    Activations Density 0.042%

    No Known Activations