© 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. 16412
    Prev
    Next
    INDEX
    Explanations

    programming constructs and methods

    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
    cznie
    -0.07
    ingas
    -0.07
    azin
    -0.07
    .capitalize
    -0.07
     plus
    -0.07
    _tcb
    -0.06
    rug
    -0.06
    μιÏĥ
    -0.06
     bar
    -0.06
    åĬł
    -0.06
    POSITIVE LOGITS
    ienes
    0.08
    Contains
    0.07
     Kloster
    0.07
    contains
    0.07
    ãĥ³ãĥĹ
    0.07
    _UNSIGNED
    0.07
    empl
    0.07
    umper
    0.07
    lai
    0.07
    utter
    0.07
    Activations Density 0.195%

    No Known Activations