© 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. 45936
    Prev
    Next
    INDEX
    Explanations

    mathematical sums and lists

    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
    ély
    -0.07
    plan
    -0.07
    åĮĢ
    -0.06
    é¡·
    -0.06
     tro
    -0.06
    ì§ĢëıĦ
    -0.06
    éĽĦ
    -0.06
    BarButton
    -0.06
    ial
    -0.06
    omic
    -0.06
    POSITIVE LOGITS
    缸åĬł
    0.08
    essar
    0.08
    æIJŃéħįçļĦ
    0.08
    ìĬ¬
    0.07
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.07
     alone
    0.07
    è¯ķè¯ķ
    0.07
    åĢ¾æĥħ
    0.07
    OFFSET
    0.07
     sums
    0.07
    Activations Density 0.001%

    No Known Activations