© 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. 15474
    Prev
    Next
    INDEX
    Explanations

    numbers and specific codes

    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
    aks
    -0.07
    èĪĴéĢĤæĢ§
    -0.06
    az
    -0.06
     mest
    -0.06
     Amo
    -0.06
    ively
    -0.06
    ouvre
    -0.06
    elt
    -0.06
    Ñħодила
    -0.06
    éĥ¨ä¸»ä»»
    -0.06
    POSITIVE LOGITS
    å¾Īå¤ļ人
    0.07
    à¥į
    0.07
    ugin
    0.07
    igators
    0.07
    å¾Īå¤ļäººåľ¨
    0.07
    ä¸į设
    0.07
     legisl
    0.07
    uale
    0.07
    /max
    0.07
    tring
    0.06
    Activations Density 0.002%

    No Known Activations