© 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. 23702
    Prev
    Next
    INDEX
    Explanations

    view people

    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
     Download
    -0.07
    å¤įåĪ¶
    -0.06
    æł¼åħ°
    -0.06
    ä¸ĭè½½
    -0.06
    Download
    -0.06
    สม
    -0.06
    è¾Ľ
    -0.06
    éģľ
    -0.06
     Guz
    -0.06
    æħ°
    -0.06
    POSITIVE LOGITS
     })(
    0.08
    ,proto
    0.08
    [](
    0.08
    -driver
    0.08
    )(((
    0.07
    åºĶå°Ĩ
    0.07
    (('
    0.07
    aleur
    0.07
    æľ¬çīĩ
    0.07
    }=
    0.07
    Activations Density 0.008%

    No Known Activations