© 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. 27861
    Prev
    Next
    INDEX
    Explanations

    organized or structured in sections/folders

    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
    æºľ
    -0.07
    尾页
    -0.07
    èĮĥåĽ´åĨħ
    -0.07
    æĵį
    -0.07
    è´±
    -0.07
    èĮĥåĽ´åĨħçļĦ
    -0.07
    Replacement
    -0.07
    ç¼Ŀ
    -0.06
    åħ·ä½ĵæĥħåĨµ
    -0.06
    gül
    -0.06
    POSITIVE LOGITS
     organized
    0.12
    organized
    0.12
    ç»ĵæŀĦ
    0.12
     organised
    0.11
     structured
    0.11
     structure
    0.11
    ç»ĵæŀĦä¸İ
    0.11
    structured
    0.11
     seperate
    0.11
    ç»ĵæŀĦåĮĸ
    0.11
    Activations Density 0.059%

    No Known Activations