© 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. 42935
    Prev
    Next
    INDEX
    Explanations

    user interaction with systems

    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
    ouz
    -0.06
    æĪij们éĥ½æĺ¯
    -0.06
    æµ®äºij
    -0.06
    ר×ķף
    -0.06
    /at
    -0.06
    æ¸ī
    -0.06
    åĽ¾è§£
    -0.05
    ascus
    -0.05
     Ander
    -0.05
    å¹´å¹´
    -0.05
    POSITIVE LOGITS
    æĪĸåħ¶
    0.10
    ìĹIJê²Į
    0.09
    zelf
    0.09
    /student
    0.09
    åıĬ家éķ¿
    0.09
    ãģ«ãģ¨ãģ£ãģ¦
    0.09
    اÙĨÙĪ
    0.09
     számára
    0.08
    åĴĮ她çļĦ
    0.08
    ÑĢома
    0.08
    Activations Density 0.248%

    No Known Activations