© 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. 1532
    Prev
    Next
    INDEX
    Explanations

    review of previous

    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
    æıIJ示信æģ¯
    -0.09
    eshire
    -0.08
     finally
    -0.08
     celo
    -0.08
    åı¦è¡ĮéĢļçŁ¥
    -0.08
    teg
    -0.07
    ä¿¡æģ¯çŃī
    -0.07
    ä¸įæĹ©
    -0.07
    estad
    -0.07
    cki
    -0.07
    POSITIVE LOGITS
    ros
    0.07
    为ä»Ģä¹Ī
    0.07
    why
    0.07
    ä¸ĭæīĭ
    0.07
     anch
    0.06
    å¦Ĥä½ķéĢļè¿ĩ
    0.06
    æĥ°
    0.06
    alian
    0.06
    Why
    0.06
     Why
    0.06
    Activations Density 0.022%

    No Known Activations