© 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. 56757
    Prev
    Next
    INDEX
    Explanations

    names ending in er, o, or es

    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
    å§Ķä¼ļ
    -0.08
    ctor
    -0.07
    geg
    -0.07
    ActionResult
    -0.07
    antasy
    -0.07
    tring
    -0.07
    phis
    -0.07
    isu
    -0.06
    /li
    -0.06
    ction
    -0.06
    POSITIVE LOGITS
    hofer
    0.09
    ately
    0.08
    stown
    0.08
    .getLogger
    0.07
    媲
    0.07
    вÑĭÑĩай
    0.07
    full
    0.07
     Brothers
    0.07
    壯
    0.07
     seminal
    0.07
    Activations Density 0.807%

    No Known Activations