© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10968
    Prev
    Next
    INDEX
    Explanations

    code specifications and equations

    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
    çĻ»
    -0.07
    Bounding
    -0.07
    oup
    -0.07
    bounding
    -0.07
    ITER
    -0.07
    ä¸ĢæŦåĩºçİ°
    -0.06
    portun
    -0.06
    Ĵáŀ
    -0.06
    åĮł
    -0.06
     ],
    -0.06
    POSITIVE LOGITS
    楼主
    0.07
    اصر
    0.07
    atics
    0.07
    iante
    0.07
    ä½łæĺ¯æĪij
    0.07
     pengar
    0.07
    .Pattern
    0.07
    è¿ĶåĽŀé¦ĸ页
    0.07
     posed
    0.06
    æĥħæ·±
    0.06
    Activations Density 0.002%

    No Known Activations