© 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. 63302
    Prev
    Next
    INDEX
    Explanations

    placeholder context

    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
    æīĢæľª
    -0.07
    åĬ¿å¤´
    -0.07
    ión
    -0.07
    unes
    -0.07
    ania
    -0.06
    esz
    -0.06
    沿岸
    -0.06
    gez
    -0.06
    两çĶ¨
    -0.06
    aned
    -0.06
    POSITIVE LOGITS
    tera
    0.09
    æł·çļĦ
    0.09
    busters
    0.08
    ëĤĺë§Ī
    0.08
    buster
    0.08
    .Expect
    0.08
    kke
    0.08
    stellung
    0.08
    pped
    0.07
    stellungen
    0.07
    Activations Density 0.030%

    No Known Activations