© 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. 65178
    Prev
    Next
    INDEX
    Explanations

    for the sake of

    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
    è¦ģä¹Ī
    -0.09
    iran
    -0.08
     either
    -0.07
    ãģĹãĤĩ
    -0.07
    å¦ŀ
    -0.07
    èĩªèIJ¥
    -0.07
    tså
    -0.07
    aved
    -0.07
    onga
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
    POSITIVE LOGITS
    èµ·è§ģ
    0.08
    ÙĥÙī
    0.08
    è¨Ģä¹ĭ
    0.07
    严谨
    0.07
    符åIJĪè¦ģæ±Ĥ
    0.07
    åĬŁ
    0.07
    yg
    0.07
     _______,
    0.07
    çijľ
    0.06
    мки
    0.06
    Activations Density 0.014%

    No Known Activations