© 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. 61067
    Prev
    Next
    INDEX
    Explanations

    combining things together

    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
    åĵĹ
    -0.07
    uide
    -0.06
    缴æİ¥åħ³ç³»åĪ°
    -0.06
    æĹłæķ°çļĦ
    -0.06
    æķħåIJį
    -0.06
    è¿ĩ客
    -0.06
    -important
    -0.06
    ела
    -0.06
    åĩĨç¡®çļĦ
    -0.06
    eszt
    -0.06
    POSITIVE LOGITS
    åıĸéķ¿è¡¥çŁŃ
    0.16
    ä¼ĺåĬ¿äºĴè¡¥
    0.13
     complementary
    0.13
    äºĴè¡¥
    0.12
     complementar
    0.10
    æī¬éķ¿
    0.10
     complimentary
    0.10
     synerg
    0.10
     complement
    0.10
    缸è¾ħ
    0.09
    Activations Density 0.135%

    No Known Activations