© 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. 7715
    Prev
    Next
    INDEX
    Explanations

    site research Visio DRBD

    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
    ä¸įæĢ¥
    -0.08
    ogos
    -0.07
    åĪĩ
    -0.07
    åħ¨éĿł
    -0.07
    __$
    -0.07
    ãĤ·ãĤ§
    -0.07
    äºŁ
    -0.06
    å±ħ
    -0.06
    vie
    -0.06
    rier
    -0.06
    POSITIVE LOGITS
    主è¦ģéĴĪ对
    0.13
    主è¦ģçĶ¨äºİ
    0.13
    éĢĤçĶ¨èĮĥåĽ´
    0.13
    ä»ĸåıª
    0.11
     versatile
    0.11
     indiscrim
    0.10
    åı¯ä»¥çĶ¨äºİ
    0.10
     versatility
    0.10
     limited
    0.10
    éĢĤçĶ¨äºİ
    0.10
    Activations Density 0.204%

    No Known Activations