© 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. 23210
    Prev
    Next
    INDEX
    Explanations

    `//` or `Output` followed by punctuation

    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
    usher
    -0.07
    ŃIJ
    -0.07
    "group
    -0.07
    æĿľ
    -0.07
    å¨Ħ
    -0.07
    _DISABLE
    -0.07
    è¶Ĭ
    -0.07
     ÙĨبÙĪد
    -0.06
    åł
    -0.06
    (&$
    -0.06
    POSITIVE LOGITS
     Output
    0.08
    ç»ĵæŀľæĺ¾ç¤º
    0.08
    è¾ĵåĩº
    0.08
     output
    0.08
    enate
    0.08
    æ¼Ķ示
    0.07
    å°ıæıIJ示
    0.07
    .stdout
    0.07
    Output
    0.07
    å±ıå¹ķä¸Ĭ
    0.07
    Activations Density 0.340%

    No Known Activations