© 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. 7746
    Prev
    Next
    INDEX
    Explanations

    phase II or III trials

    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
    kaus
    -0.09
    áĢ·
    -0.08
    ocere
    -0.08
    adge
    -0.08
     zweit
    -0.08
    uges
    -0.08
    chenke
    -0.07
    ä¸įå®ĮçļĦ
    -0.07
    enste
    -0.07
    ogi
    -0.07
    POSITIVE LOGITS
    /+
    0.08
    /'
    0.07
    /-
    0.07
    imensional
    0.06
    /--
    0.06
    ì§ľ
    0.06
    /*
    0.06
    æĪĸ以ä¸Ĭ
    0.06
    /**
    0.06
    åıĬ以ä¸ĭ
    0.06
    Activations Density 0.153%

    No Known Activations