© 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. 27288
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
    edet
    -0.08
     disemb
    -0.07
    ụng
    -0.07
    issant
    -0.07
    kau
    -0.07
    olÃŃ
    -0.07
    åĻľ
    -0.07
    éŁ¿
    -0.07
    utenant
    -0.06
     tá»Ń
    -0.06
    POSITIVE LOGITS
    unic
    0.08
    æ´»åĬ¨çŃī
    0.07
    ä¿¡æģ¯çŃī
    0.07
    åħ¬åı¸çŃī
    0.07
     etc
    0.07
    çŃīå¤ļç§į
    0.07
    Ñĩа
    0.07
    è´¹çŃī
    0.07
    设å¤ĩçŃī
    0.07
     alike
    0.07
    Activations Density 0.222%

    No Known Activations