© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17862
    Prev
    Next
    INDEX
    Explanations

    non-stress test

    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
    ä¸Ģéĥİ
    -0.07
    dach
    -0.07
    epro
    -0.07
    åĩºä¸ĢæĿ¡
    -0.06
     pest
    -0.06
    лам
    -0.06
    Ter
    -0.06
    iri
    -0.06
    ekl
    -0.06
    åIJĴ
    -0.06
    POSITIVE LOGITS
    _WATCH
    0.07
    ulusan
    0.07
    ampu
    0.07
    kaus
    0.07
    å¾·éŁ³
    0.07
    .wrapper
    0.06
    aliz
    0.06
     atribu
    0.06
    undry
    0.06
    uckles
    0.06
    Activations Density 0.098%

    No Known Activations