© 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. 26578
    Prev
    Next
    INDEX
    Explanations

    amount options, parameters, number, processing

    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
     Raya
    -0.07
    以åħ¶
    -0.07
     Chau
    -0.07
    è¿Ļ家ä¼Ļ
    -0.07
     ës
    -0.06
    åľ¨æŁIJ
    -0.06
    ITÃĢ
    -0.06
    urst
    -0.06
    éĢĤ度
    -0.06
    æIJľçĭĹ
    -0.06
    POSITIVE LOGITS
    etter
    0.08
    erv
    0.07
    è¿ĽåĪ°
    0.07
    被æĴŀ
    0.07
    à±Īà°¨
    0.07
     oben
    0.07
    Å¡ti
    0.07
    abet
    0.07
    ughty
    0.07
    olgen
    0.07
    Activations Density 0.036%

    No Known Activations