© 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. 11246
    Prev
    Next
    INDEX
    Explanations

    .form .Document .layout .options layer

    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
    å·¥ç¨ĭåĴĮ
    -0.07
    es
    -0.07
    å·¥ç¨ĭåѦéĻ¢
    -0.07
    HexString
    -0.07
    th
    -0.06
    chr
    -0.06
    enz
    -0.06
    esel
    -0.06
    å·¥ç¨ĭçŃī
    -0.06
    FS
    -0.06
    POSITIVE LOGITS
    çªŁ
    0.07
    ุà¸Ķ
    0.07
    fter
    0.06
    itunes
    0.06
    _funcs
    0.06
    äºijæ·¡
    0.06
     slan
    0.06
    æĭīåįĩ
    0.06
    æ·ij
    0.06
    gings
    0.06
    Activations Density 0.047%

    No Known Activations