© 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. 45223
    Prev
    Next
    INDEX
    Explanations

    "connections" or "inner work"

    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
    azio
    -0.07
    èĿĩ
    -0.07
    ayne
    -0.06
    ove
    -0.06
    ipt
    -0.06
    mband
    -0.06
    é¢ij
    -0.06
    adat
    -0.06
    _leader
    -0.06
    è¿ĺä¸įçŁ¥éģĵ
    -0.06
    POSITIVE LOGITS
    Enumerator
    0.08
     Junta
    0.07
    ãĥŁãĥ¥
    0.07
    èĦ¯
    0.07
    DDL
    0.07
    é¬ĵ
    0.07
    ssl
    0.07
    ª
    0.07
    ikki
    0.07
    æĺ¯æĪijçļĦ
    0.07
    Activations Density 0.071%

    No Known Activations