© 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. 51001
    Prev
    Next
    INDEX
    Explanations

    system ..NET namespaces

    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
    åĴ«å°º
    -0.08
     getArguments
    -0.08
    游åĪĥ
    -0.08
    åıijçŁŃä¿¡
    -0.07
    eht
    -0.07
    änz
    -0.07
    tw
    -0.07
    ìŀł
    -0.07
     caden
    -0.07
    _guess
    -0.07
    POSITIVE LOGITS
    éĿ©
    0.07
    ãģ§ãĤĤãģªãģĦ
    0.06
    âģ
    0.06
    oust
    0.06
    ivos
    0.06
    åĵģåij³
    0.06
    ä¸į详
    0.06
    recursive
    0.06
    æij©
    0.06
    apon
    0.06
    Activations Density 0.001%

    No Known Activations