© 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. 39558
    Prev
    Next
    INDEX
    Explanations

    Category: Bucket List

    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
    ogi
    -0.07
    _EXIT
    -0.07
    让åħ¶
    -0.07
    reto
    -0.07
    èѬå¦Ĥ
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
     Meanwhile
    -0.07
     eslint
    -0.06
    leti
    -0.06
    æ¯Ķå¦Ĥ
    -0.06
    POSITIVE LOGITS
    ä¾Ŀæ³ķ
    0.07
    çŃĶæ¡Ī为
    0.07
    ITES
    0.06
    使åĩº
    0.06
    blas
    0.06
     curt
    0.06
    षà¥įà¤Ł
    0.06
    ữu
    0.06
    å¼Ģå¼Ģå¿ĥ
    0.06
    ION
    0.06
    Activations Density 0.006%

    No Known Activations