© 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. 45157
    Prev
    Next
    INDEX
    Explanations

    namespace declarations

    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
    ļľ
    -0.08
    ley
    -0.07
    asil
    -0.07
    sthrough
    -0.07
    IFI
    -0.07
    abia
    -0.06
    iors
    -0.06
     sach
    -0.06
    ousel
    -0.06
    ç§ķ
    -0.06
    POSITIVE LOGITS
    _assert
    0.07
    μβ
    0.07
    [left
    0.07
    agine
    0.07
    kel
    0.06
     assert
    0.06
    $n
    0.06
    å·¦
    0.06
    AVED
    0.06
    åĿª
    0.06
    Activations Density 0.080%

    No Known Activations