© 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. 63397
    Prev
    Next
    INDEX
    Explanations

    types of characteristics

    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¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.08
    å°½ãģı
    -0.08
    /Card
    -0.08
    urve
    -0.08
     /**<
    -0.07
    sche
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    inheiten
    -0.07
    nga
    -0.07
    uss
    -0.07
    POSITIVE LOGITS
    åĴĮæĸ¹æ³ķ
    0.17
     and
    0.16
    åĴĮåĨħ容
    0.14
    à¹ģละà¸Ħวาม
    0.14
    à¹ģละ
    0.14
    åıĬ
    0.13
    åĴĮæŶéĹ´
    0.13
     vÃł
    0.13
     и
    0.13
    åĴĮèĥ½åĬĽ
    0.12
    Activations Density 0.410%

    No Known Activations