© 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. 49505
    Prev
    Next
    INDEX
    Explanations

    all, then, prior, first, entire, complete

    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
    illers
    -0.08
    ç¥ĸ
    -0.07
    å¡«è¡¥
    -0.07
    ept
    -0.07
    /proto
    -0.07
    仪
    -0.07
    avn
    -0.07
    ä¸īçŃī
    -0.07
     automatic
    -0.07
    chemas
    -0.07
    POSITIVE LOGITS
    åħĪ
    0.12
    éľĢè¦ģåħĪ
    0.11
    æĺ¯åħĪ
    0.11
     upfront
    0.11
    è¦ģåħĪ
    0.11
    åħĪãģ«
    0.10
    åħĪæĬĬ
    0.10
    ä¸Ģ次æĢ§
    0.10
    并åIJĮæŶ
    0.10
     beforehand
    0.10
    Activations Density 0.132%

    No Known Activations