© 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. 38813
    Prev
    Next
    INDEX
    Explanations

    github issues

    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
    etul
    -0.09
    ØŃتÙĩا
    -0.09
    èī²åĪĹ
    -0.08
    chie
    -0.08
    este
    -0.08
     );
    -0.07
    ecz
    -0.07
    ÙģتÙĩ
    -0.07
    виÑĨа
    -0.07
    IVEN
    -0.07
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.08
    ï¸ı
    0.07
     Why
    0.07
    ]**
    0.07
    ////////////////////////////////////////////////////////////////////////////////
    0.07
    æĹłéĹ´
    0.07
    ulo
    0.07
    为ä»Ģä¹Īä¸į
    0.07
     ====
    0.06
    ãģĹãģıãģ¯
    0.06
    Activations Density 0.011%

    No Known Activations