© 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. 4392
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings and code keywords

    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
    мÑı
    -0.07
    æĬķåħ¥åĪ°
    -0.07
    èĥ½å¤Łè®©
    -0.07
    ynthesis
    -0.07
    eda
    -0.07
    asca
    -0.06
     decent
    -0.06
    ابس
    -0.06
    enga
    -0.06
    è¿ĺæĬĬ
    -0.06
    POSITIVE LOGITS
    NullException
    0.08
    ç¬Ķ
    0.07
    witter
    0.07
    (forKey
    0.07
    Ùħص
    0.07
    uell
    0.07
    ties
    0.07
    å·´åĭĴ
    0.07
    berte
    0.07
    uelle
    0.07
    Activations Density 0.012%

    No Known Activations