© 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. 50561
    Prev
    Next
    INDEX
    Explanations

    code tokens: | , () ,

    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
    ÑĤаки
    -0.06
    æ°ĵ
    -0.06
    inat
    -0.06
    .init
    -0.06
    oki
    -0.06
    init
    -0.06
    IFE
    -0.06
    =no
    -0.06
    ç»ĵ
    -0.06
    .om
    -0.06
    POSITIVE LOGITS
    eshire
    0.09
    tek
    0.08
    egu
    0.08
    obox
    0.08
    çĶļ
    0.07
    çŁ
    0.07
    urd
    0.07
    .normalized
    0.07
    åģ
    0.07
     Zus
    0.07
    Activations Density 0.004%

    No Known Activations