© 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. 28471
    Prev
    Next
    INDEX
    Explanations

    . Then

    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
    dez
    -0.08
    éļĪ
    -0.08
     POS
    -0.07
    vic
    -0.07
    erade
    -0.07
    uly
    -0.07
    erty
    -0.07
    ç©
    -0.07
    oween
    -0.07
    /firebase
    -0.07
    POSITIVE LOGITS
    ç´§æİ¥çĿĢ
    0.08
    åħ¶æ¬¡
    0.07
    .Then
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
     Further
    0.07
    次ãģ«
    0.06
    çĦ¶åIJİ
    0.06
    립
    0.06
    æİ¥çĿĢ
    0.06
    æĮº
    0.06
    Activations Density 0.003%

    No Known Activations