© 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. 19953
    Prev
    Next
    INDEX
    Explanations

    definition of terms

    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
    éĢļè¿ĩ对
    -0.08
    çİĭ家
    -0.08
    就好åĥı
    -0.07
    èĬ¬
    -0.07
    ÑĢка
    -0.07
    è¯Ħä¼°
    -0.07
    就好æ¯Ķ
    -0.07
    ضا
    -0.07
    ç´
    -0.07
    stry
    -0.07
    POSITIVE LOGITS
     Definition
    0.11
    Definition
    0.10
     definition
    0.10
    çļĦå®ļä¹ī
    0.10
     definitions
    0.10
    å®ļ義
    0.09
    definition
    0.09
    ä¸įåĮħåIJ«
    0.08
     nowadays
    0.08
    å®ļä¹ī为
    0.08
    Activations Density 0.006%

    No Known Activations