© 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. 50934
    Prev
    Next
    INDEX
    Explanations

    list delimiters

    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
    ikki
    -0.07
     Emerson
    -0.06
    (const
    -0.06
    1
    -0.06
    åĬŁ
    -0.05
    ode
    -0.05
    2
    -0.05
    hö
    -0.05
     bow
    -0.05
     cot
    -0.05
    POSITIVE LOGITS
    举éĺ³
    0.09
    ä¸ĭ载次æķ°
    0.08
    家天ä¸ĭ
    0.08
    影幽
    0.08
    家åĸ»
    0.08
    arry
    0.08
    urias
    0.08
    .UTC
    0.08
    -hit
    0.08
    StateException
    0.08
    Activations Density 0.001%

    No Known Activations