© 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. 32471
    Prev
    Next
    INDEX
    Explanations

    program ->

    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
    èİī
    -0.07
    zer
    -0.07
    utile
    -0.07
    ÃŃp
    -0.07
    åĴĮè§ĦèĮĥ
    -0.07
    isit
    -0.06
    omp
    -0.06
    림
    -0.06
    æħ§
    -0.06
    anter
    -0.06
    POSITIVE LOGITS
    chwitz
    0.08
    uel
    0.08
    manos
    0.07
    å¹´åĩºçĶŁ
    0.07
    åľ¨æĦı
    0.07
    alagi
    0.07
    å®ķ
    0.07
    amarca
    0.07
    yer
    0.07
    otec
    0.07
    Activations Density 0.004%

    No Known Activations