© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22887
    Prev
    Next
    INDEX
    Explanations

    expected, supposed, sequel, modeled, moved, added, created

    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
    lopedia
    -0.08
    acier
    -0.08
    çĭ¬ç§Ģ
    -0.08
    èݫ大çļĦ
    -0.08
    aglio
    -0.08
    _EXTENSION
    -0.07
    åĮ»éĻ¢åľ°åĿĢ
    -0.07
    CRET
    -0.07
    游åĪĥ
    -0.07
    .NotFound
    -0.07
    POSITIVE LOGITS
    ú
    0.07
    itse
    0.07
    ines
    0.06
    noop
    0.06
    -free
    0.06
    ersh
    0.06
    atri
    0.06
    åŃĹ第
    0.06
    éĩij鸡
    0.06
    lessly
    0.06
    Activations Density 0.432%

    No Known Activations