© 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. 55884
    Prev
    Next
    INDEX
    Explanations

    specific software names

    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
    ç¦ģæŃ¢
    -0.08
    ãĥ³ãĤ°ãĥ«
    -0.07
    å§Ĩæĸ¯
    -0.07
    èĬĿ
    -0.07
    eler
    -0.07
    æĪijä¸įæĥ³
    -0.07
    ÑĩÑĸ
    -0.06
    èĢĮåħ¶
    -0.06
    åı¯ä¸įæĺ¯
    -0.06
    ogg
    -0.06
    POSITIVE LOGITS
     resta
    0.08
    åĶ¯ä¸Ģä¸Ģ个
    0.07
     einzig
    0.07
    pees
    0.07
    æīįæĺ¯
    0.07
     unmatched
    0.07
    à¸ļรม
    0.07
    lit
    0.07
    isSelected
    0.07
     fras
    0.07
    Activations Density 0.003%

    No Known Activations