© 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. 33348
    Prev
    Next
    INDEX
    Explanations

    math and code variables

    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
    åıijæĶ¹
    -0.08
    éªĦéĺ³
    -0.07
    åĦ¿çļĦ
    -0.07
    yz
    -0.07
    hin
    -0.07
     éc
    -0.07
    è´¤
    -0.06
    igl
    -0.06
     taper
    -0.06
    设为é¦ĸ页
    -0.06
    POSITIVE LOGITS
    undry
    0.07
    rips
    0.07
    å±ĤéĿ¢çļĦ
    0.07
    irkan
    0.06
    ä¸Ĭå¹´
    0.06
    çīĪ
    0.06
    æĺ¯ä½łçļĦ
    0.06
    æĿŀ
    0.06
    ês
    0.06
    uler
    0.06
    Activations Density 0.001%

    No Known Activations