© 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. 47604
    Prev
    Next
    INDEX
    Explanations

    browser compatibility

    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
    IRS
    -0.07
     solitary
    -0.07
    管çIJĨæľįåĬ¡
    -0.06
    æ¯İ
    -0.06
     usually
    -0.06
    .self
    -0.06
     Leib
    -0.06
    ä¸įåĩĨ
    -0.06
    家åĬ¡
    -0.06
    avig
    -0.06
    POSITIVE LOGITS
     interoper
    0.09
    åħ¼å®¹æĢ§
    0.08
    çī¢
    0.08
    compatible
    0.08
     compatibility
    0.08
    .ensure
    0.08
    agnostic
    0.08
    åħ¼å®¹
    0.08
    åªĽ
    0.08
    åľ°çIJĥä¸Ĭ
    0.08
    Activations Density 0.408%

    No Known Activations