© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48523
    Prev
    Next
    INDEX
    Explanations

    probability and sequences

    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
    fon
    -0.07
    ustr
    -0.07
    åĿĬ
    -0.07
    achen
    -0.06
    æīĢè°ĵçļĦ
    -0.06
    ึà¸ĩ
    -0.06
     rough
    -0.06
    /io
    -0.06
    æĺĮ
    -0.06
    rough
    -0.06
    POSITIVE LOGITS
    probability
    0.10
    çļĦåĩłçİĩ
    0.09
    prog
    0.09
    _probs
    0.09
     probabilities
    0.09
    æ¯Ķä¾ĭ为
    0.09
    åĩłçİĩ
    0.09
    aturas
    0.09
     probability
    0.09
    æ¯Ķä¾ĭçļĦ
    0.09
    Activations Density 0.006%

    No Known Activations