© 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. 24028
    Prev
    Next
    INDEX
    Explanations

    inner or internal 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
    åľ¨çº¿çķĻè¨Ģ
    -0.09
    atria
    -0.08
    ÈĻa
    -0.08
    ä¹ĭ为
    -0.08
    uç
    -0.08
     Giornata
    -0.08
    erca
    -0.08
     táºŃt
    -0.08
    abis
    -0.08
    åĪĨä¹ĭä¸Ģ
    -0.08
    POSITIVE LOGITS
    most
    0.10
    ized
    0.08
    åĽłç´ł
    0.08
    lying
    0.08
    驱åĬ¨åĬĽ
    0.08
    uff
    0.07
    izing
    0.07
    åĬ¨åĬĽ
    0.07
    ening
    0.07
    ly
    0.07
    Activations Density 0.007%

    No Known Activations