© 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. 49602
    Prev
    Next
    INDEX
    Explanations

    compound identifiers

    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
    åį³åı¯æŁ¥çľĭ
    -0.07
     koleg
    -0.07
    mont
    -0.07
    ç«ĭç§ĭ
    -0.07
    ECK
    -0.07
    olson
    -0.07
    ACLE
    -0.06
    eson
    -0.06
    /course
    -0.06
    oki
    -0.06
    POSITIVE LOGITS
    iliation
    0.07
    obra
    0.07
    ì¶ķ
    0.07
    ä¸Ģè·¯
    0.07
    orous
    0.06
    麼
    0.06
    åħ¹
    0.06
    ils
    0.06
    è¨Ģ
    0.06
    ads
    0.06
    Activations Density 1.110%

    No Known Activations