© 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. 15923
    Prev
    Next
    INDEX
    Explanations

    parts, phases, or steps

    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
    ÐĺÐIJ
    -0.07
     Suri
    -0.06
    ongyang
    -0.06
    ãĤ¹ãĥŀ
    -0.06
    onte
    -0.06
    éĢıè§Ĩ
    -0.06
    亦æĺ¯
    -0.06
     nouveautés
    -0.06
     Afin
    -0.06
    ERRU
    -0.06
    POSITIVE LOGITS
     Barker
    0.07
    çį
    0.07
    meta
    0.07
    retta
    0.07
    å¥ĭè¿Ľ
    0.07
    Ł
    0.07
    .','
    0.07
    è²
    0.06
    aik
    0.06
    ollapse
    0.06
    Activations Density 0.019%

    No Known Activations