© 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. 58039
    Prev
    Next
    INDEX
    Explanations

    London SW1P

    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
     Boc
    -0.07
    VRT
    -0.06
    ÙĥÙī
    -0.06
     Gav
    -0.06
    HUD
    -0.06
    pps
    -0.06
    è¯¥ä½ľèĢħ
    -0.06
    okok
    -0.06
    JNI
    -0.06
    åIJĦè¡Į
    -0.06
    POSITIVE LOGITS
    ç¼ĸåı·
    0.16
    ç·¨èĻŁ
    0.14
    åı·ä¸º
    0.13
     (#
    0.12
    代åı·
    0.11
    åŀĭåı·
    0.11
    หมายà¹Ģลà¸Ĥ
    0.11
    é¡¹çĽ®ç¼ĸåı·
    0.11
     numbered
    0.11
     kode
    0.11
    Activations Density 1.573%

    No Known Activations