© 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. 30628
    Prev
    Next
    INDEX
    Explanations

    note that

    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
    çİ°å°±
    -0.08
    æĪij便
    -0.07
    她便
    -0.07
    ä»ĸ便
    -0.07
    ares
    -0.07
    sent
    -0.07
    aver
    -0.07
    ammed
    -0.07
    åĪĻåı¯
    -0.07
    请æĮī
    -0.07
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.09
    è¿Ļä¸įæĺ¯
    0.09
    !).
    0.09
    åĪ°çĽ®åīį
    0.09
    !),
    0.08
    że
    0.08
    !!:
    0.08
    !».
    0.08
    еÑĤÑĮ
    0.08
    ìĹIJëıĦ
    0.08
    Activations Density 0.005%

    No Known Activations