© 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. 23099
    Prev
    Next
    INDEX
    Explanations

    bijective mapping

    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
    ORI
    -0.07
    ophil
    -0.07
    ãĥĭãĥ³ãĤ°
    -0.07
     tá»ĩ
    -0.07
    alar
    -0.07
    umberland
    -0.06
    _constants
    -0.06
    ä¼ļåIJĮ
    -0.06
    _literals
    -0.06
    iores
    -0.06
    POSITIVE LOGITS
    ection
    0.09
    ackson
    0.09
     between
    0.08
    äck
    0.08
     across
    0.08
    Across
    0.08
    еÑģÑĤв
    0.07
    ity
    0.07
    Ŀ
    0.07
    ections
    0.07
    Activations Density 0.003%

    No Known Activations