© 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. 32320
    Prev
    Next
    INDEX
    Explanations

    directly

    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
    åħ±åIJĮåĬªåĬĽ
    -0.09
    æĢ»åħ±
    -0.08
     ultimately
    -0.08
    è´¹
    -0.07
     insgesamt
    -0.07
    ä¸Ģè´¯
    -0.07
    çī¹åĪ«æ³¨æĦı
    -0.07
    çĦī
    -0.07
     íĬ¹íŀĪ
    -0.07
     accordingly
    -0.07
    POSITIVE LOGITS
     directly
    0.13
    缴æİ¥çļĦ
    0.12
    缴æİ¥
    0.12
    åı¯ä»¥çĽ´æİ¥
    0.12
     directamente
    0.11
     Ùħباشرة
    0.11
     directement
    0.11
     اÙĦÙħباشر
    0.11
     Direct
    0.11
    å°±çĽ´æİ¥
    0.11
    Activations Density 0.151%

    No Known Activations