© 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. 42240
    Prev
    Next
    INDEX
    Explanations

    configuration keys or properties

    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
    iena
    -0.07
    arana
    -0.07
    UTH
    -0.06
    ään
    -0.06
    ron
    -0.06
    ivery
    -0.06
    remely
    -0.06
    FAST
    -0.06
    åŃ¦æł¡é¢Ĩ导
    -0.06
    lys
    -0.06
    POSITIVE LOGITS
    holt
    0.08
    -eslint
    0.07
    [`
    0.07
    ï½ŀãĢĤ
    0.07
    ÚĺÙĩ
    0.07
    æ··èĽĭ
    0.07
    ãĤģãģIJ
    0.07
    ucci
    0.07
    .de
    0.07
    Ĺı
    0.07
    Activations Density 0.099%

    No Known Activations