© 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. 29697
    Prev
    Next
    INDEX
    Explanations

    some kind of

    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
     only
    -0.08
    Scoped
    -0.08
    صÙģ
    -0.08
     majeure
    -0.08
    strup
    -0.07
    å¦ĤæѤ
    -0.07
    emput
    -0.07
    _UTF
    -0.07
    orse
    -0.07
    idar
    -0.07
    POSITIVE LOGITS
    onic
    0.09
    bod
    0.08
    åı«åģļ
    0.07
    ä½Ĩæĺ¯å½ĵ
    0.07
    æ¯Ķå¦Ĥ说
    0.07
    ä½Ĩæĺ¯çİ°åľ¨
    0.07
    ä½Ĩæĺ¯å®ĥ
    0.07
     intermediate
    0.07
     specific
    0.07
    ä½Ĩæĺ¯çĶ±äºİ
    0.07
    Activations Density 0.062%

    No Known Activations