© 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. 58097
    Prev
    Next
    INDEX
    Explanations

    flyers, agencies, instance, Â, won, another

    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
    вÑı
    -0.08
    迹
    -0.08
    orrent
    -0.07
    ahr
    -0.07
    éĽį
    -0.07
     пÑĢиб
    -0.07
    ä¸ĥæĹ¥
    -0.07
    еÑĢна
    -0.07
    OwnProperty
    -0.07
    urale
    -0.07
    POSITIVE LOGITS
    cff
    0.06
     rut
    0.06
    åıij表æŶéĹ´
    0.06
    rost
    0.06
    çĴĭ
    0.06
     Pest
    0.06
    é£ĺèį¡
    0.06
    anzas
    0.06
    rut
    0.06
    csr
    0.06
    Activations Density 0.027%

    No Known Activations