© 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. 43925
    Prev
    Next
    INDEX
    Explanations

    teams, tables, files, data

    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
    mento
    -0.08
    itkan
    -0.06
    Offsets
    -0.06
    èªĩ
    -0.06
    Ñģловно
    -0.06
    èĹĿ
    -0.06
    .osgi
    -0.06
    CanBe
    -0.06
    è¡
    -0.06
    lak
    -0.06
    POSITIVE LOGITS
     therein
    0.08
    çŃĶåį·
    0.08
    isl
    0.07
    hev
    0.07
    æ¯ıå°ıé¢ĺ
    0.07
    LOGGER
    0.07
    Ñģл
    0.07
    éĤ£éĩĮçļĦ
    0.07
    æ¯ıæ¯ı
    0.07
    ä¸Ĭä¼łåĽ¾çīĩ
    0.07
    Activations Density 0.022%

    No Known Activations