© 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. 19994
    Prev
    Next
    INDEX
    Explanations

    processes and actions

    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
     infatti
    -0.07
     importantly
    -0.07
    eld
    -0.07
     accordingly
    -0.07
    éĩįè¦ģçļĦæĺ¯
    -0.07
    ä¸İä¹ĭ
    -0.07
    ФÐIJ
    -0.06
    为äºĨ解åĨ³
    -0.06
    ели
    -0.06
    vely
    -0.06
    POSITIVE LOGITS
    æĿ¡ä»¶ä¸ĭçļĦ
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.08
    igencia
    0.07
    arder
    0.07
    /loading
    0.07
    OSP
    0.07
    å¿ĥæĤ¦
    0.07
    é¹Ń
    0.07
    ä»İèĢĮ使
    0.07
    agas
    0.07
    Activations Density 1.173%

    No Known Activations