© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    cite as

    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
    estra
    -0.08
    Å¡a
    -0.07
    uff
    -0.07
    åħŃåIJĪ
    -0.07
    asta
    -0.07
    _testing
    -0.07
    èĬ®
    -0.07
     Gore
    -0.07
    ccion
    -0.07
    缮
    -0.07
    POSITIVE LOGITS
     tslint
    0.07
    åĴĮåIJĮäºĭ
    0.07
    æł¼å°Ķ
    0.07
    ZE
    0.07
    .fragment
    0.07
    ovich
    0.06
    дели
    0.06
    ifik
    0.06
    æıIJæ¡Ī
    0.06
    åįłåħ¬åı¸
    0.06
    Activations Density 0.039%

    No Known Activations