© 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. 27949
    Prev
    Next
    INDEX
    Explanations

    specs::

    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
    ä¿Ń
    -0.08
    INLINE
    -0.07
    ÑĤÑĥÑģ
    -0.07
    enom
    -0.07
    StyleSheet
    -0.07
    æŀ
    -0.07
    润
    -0.07
    innen
    -0.07
    çݯçIJĥ
    -0.07
    è¨
    -0.07
    POSITIVE LOGITS
     redirectTo
    0.07
    ابÙĬ
    0.07
     Hil
    0.07
     transporting
    0.07
    tensor
    0.07
     dof
    0.07
    æĶ¶å®¹
    0.06
    ç²ĴåŃIJ
    0.06
    transport
    0.06
     tensor
    0.06
    Activations Density 0.006%

    No Known Activations