© 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. 15162
    Prev
    Next
    INDEX
    Explanations

    scientific journal identifiers

    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
    âĢ
    -0.08
    ijin
    -0.07
    spb
    -0.07
    é¢ĸ
    -0.07
    präsident
    -0.06
    ếm
    -0.06
    è¶³å¤Ł
    -0.06
    -0.06
    åIJįè¨Ģ
    -0.06
     Ngô
    -0.06
    POSITIVE LOGITS
    _DENIED
    0.07
    óta
    0.07
    erja
    0.07
    коÑĢи
    0.07
    ä¹Łæĺ¯æĪij们
    0.07
    å¿ĥäºĭ
    0.07
    reon
    0.06
    iop
    0.06
    untu
    0.06
    unci
    0.06
    Activations Density 0.118%

    No Known Activations