© 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. 29613
    Prev
    Next
    INDEX
    Explanations

    descriptive suffixes

    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
    人æĪĸ
    -0.09
    å¦ĤæѤ
    -0.08
    iaux
    -0.08
    aros
    -0.07
    otella
    -0.07
    uhe
    -0.07
    ç²¾è¯ļ
    -0.07
    ~~~~~~~~~~~~~~~~
    -0.07
     ",",
    -0.07
     ÄijÃłnh
    -0.07
    POSITIVE LOGITS
    /etc
    0.08
    åį´åıĪ
    0.07
    ,and
    0.07
    ãģ¨ãģĦãģ£ãģŁ
    0.07
    çŃīçī¹çĤ¹
    0.07
    äºİä¸Ģä½ĵçļĦ
    0.07
    åį´
    0.06
    åį»
    0.06
     ê·¸ë¦¬ê³ł
    0.06
    arka
    0.06
    Activations Density 0.116%

    No Known Activations