© 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. 34545
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    áng
    -0.08
    å·§
    -0.07
    Ñģк
    -0.07
    è¿ľåİ»
    -0.07
    ¦
    -0.07
    åĴĮåŁ¹åħ»
    -0.07
    çĸijéļ¾
    -0.07
    Ùħت
    -0.07
    Activated
    -0.06
    perte
    -0.06
    POSITIVE LOGITS
     ÙĪبعد
    0.09
    ahan
    0.08
    æľĢæĸ°æĽ´æĸ°
    0.07
    æŃ¤æ¬¡
    0.07
    -before
    0.07
    è¨
    0.07
     intervention
    0.07
    دÙĬÙĨ
    0.07
    ä¿ĿæĬ¤æݪæĸ½
    0.07
     exposure
    0.06
    Activations Density 0.065%

    No Known Activations