© 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. 11609
    Prev
    Next
    INDEX
    Explanations

    evaluation or status words

    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
    èĩ³ä»Ĭä»į
    -0.06
    èĥĨ
    -0.06
     Yep
    -0.06
     Moody
    -0.06
    åĪĻ表示
    -0.06
     ...,
    -0.06
    ocab
    -0.06
    alon
    -0.06
     ÙĨسخة
    -0.06
    ÑĩиÑĤа
    -0.06
    POSITIVE LOGITS
    ложением
    0.07
    иÑģи
    0.07
    Äı
    0.07
    ëĭ¤
    0.07
    exposition
    0.07
    uida
    0.07
    åıĪæĪĸèĢħ
    0.07
    éĩijçİī
    0.07
    @d
    0.07
    ole
    0.07
    Activations Density 0.001%

    No Known Activations