© 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. 56969
    Prev
    Next
    INDEX
    Explanations

    not applicable; no plot

    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
    zeni
    -0.08
    enius
    -0.07
    尽管
    -0.07
    å¾Īæľīåı¯èĥ½
    -0.07
     despite
    -0.06
    æĺİæĺİ
    -0.06
    _restart
    -0.06
    èĭ¦
    -0.06
     Despite
    -0.06
    æĸ°éĹ»ç½ij
    -0.06
    POSITIVE LOGITS
    ä¸įåŃĺåľ¨
    0.14
    è°Īä¸įä¸Ĭ
    0.13
    并æĹł
    0.10
    æł¹æľ¬å°±æ²¡æľī
    0.10
    没æľīä»Ģä¹Ī
    0.10
    æł¹æľ¬æ²¡æľī
    0.10
    并没æľīä»Ģä¹Ī
    0.09
     nonexistent
    0.09
    没åķ¥
    0.09
    缮åīį没æľī
    0.09
    Activations Density 0.146%

    No Known Activations