© 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. 31111
    Prev
    Next
    INDEX
    Explanations

    medical statistics and measurements

    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
    客æĪ·æıIJä¾Ľ
    -0.07
    verst
    -0.07
    otos
    -0.07
    æĪĸåĪ©çĶ¨
    -0.07
    被å¥Ĺ
    -0.07
    æħ°
    -0.06
    _ver
    -0.06
     Caro
    -0.06
    çķĻä¸ĭä¸Ģ
    -0.06
    Wi
    -0.06
    POSITIVE LOGITS
    ëŀij
    0.07
    åĪ©
    0.07
    ixin
    0.07
    eea
    0.07
    egl
    0.07
    oku
    0.07
    æĢ»ä½ĵæĿ¥è¯´
    0.07
    åħ¶æ¬¡
    0.07
    ÏīÏĥη
    0.06
    compose
    0.06
    Activations Density 0.359%

    No Known Activations