© 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. 22179
    Prev
    Next
    INDEX
    Explanations

    worth mentioning

    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
    åĬłæĭ¿å¤§
    -0.11
    æĸ°åĬłåĿ¡
    -0.11
    缸è¾ħ缸æĪIJ
    -0.10
    zinho
    -0.10
    Ø©
    -0.10
    以任ä½ķ
    -0.09
    åĭĩå¾Ģ缴åīį
    -0.09
    iewicz
    -0.08
    æ¯Ľæ³½ä¸ľ
    -0.08
    fade
    -0.08
    POSITIVE LOGITS
    åħĭèIJ¨æĸ¯
    0.13
    åĪ°çļĦ
    0.10
    ings
    0.09
    avenport
    0.09
    æķĻäºİ
    0.09
    çŁ¥çļĦ
    0.09
    inition
    0.09
     phép
    0.08
    INGS
    0.08
    à¸ĩาม
    0.08
    Activations Density 0.001%

    No Known Activations