© 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. 49146
    Prev
    Next
    INDEX
    Explanations

    numbers and groups

    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
    ToBounds
    -0.07
    深度
    -0.07
    ÑĩаÑģÑĤи
    -0.07
    iums
    -0.07
    åħ¹
    -0.06
    inach
    -0.06
    èıģ
    -0.06
    ä¸Ģéĥ¨åĪĨ
    -0.06
    ensus
    -0.06
    èĩªèº«
    -0.06
    POSITIVE LOGITS
    egos
    0.08
    èĴ¸èĴ¸
    0.08
    æīĢå¾Ĺ
    0.07
    aktan
    0.07
    ugg
    0.07
    edula
    0.07
    ubin
    0.07
    embr
    0.07
    åĮ¿
    0.07
    æ°Ķé¦ģ
    0.07
    Activations Density 0.586%

    No Known Activations