© 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. 9255
    Prev
    Next
    INDEX
    Explanations

    Fifty healthy

    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
    ector
    -0.08
    inder
    -0.07
    éģģ
    -0.07
    åį¡çī¹
    -0.07
     “.
    -0.07
    amar
    -0.07
    ³³³³³³³³
    -0.07
    ektor
    -0.07
    尼奥
    -0.07
     Corm
    -0.07
    POSITIVE LOGITS
    aint
    0.08
    evin
    0.07
    åħ³
    0.07
    prech
    0.06
    ords
    0.06
    ackers
    0.06
    æŶä¸ĭ
    0.06
    èµ·æĿ¥äºĨ
    0.06
    éĩijæ²Ļ
    0.06
    BRE
    0.06
    Activations Density 0.129%

    No Known Activations