© 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. 3444
    Prev
    Next
    INDEX
    Explanations

    uniform distance metrics

    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
    èIJ¨å°Ķ
    -0.07
    abay
    -0.07
    åĴĮå¤ļ
    -0.07
    amah
    -0.07
    è´¡çĮ®
    -0.07
    çĶĦåĪ«
    -0.07
    áĥŃ
    -0.07
    éĻ·
    -0.07
    åĪĨå¸ĥå¦Ĥä¸ĭ
    -0.07
    积æŀģä¸İ
    -0.07
    POSITIVE LOGITS
    èĮľ
    0.07
     metric
    0.07
    andin
    0.07
    udson
    0.07
    é¾Ļä¹ĭ
    0.07
    perf
    0.07
     JNIEnv
    0.07
    åIJ»
    0.07
     forgetting
    0.07
    ewise
    0.07
    Activations Density 0.003%

    No Known Activations