© 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. 13792
    Prev
    Next
    INDEX
    Explanations

    `=http://` or `https://`

    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
    认è¯ģåķĨ家
    -0.07
    髦
    -0.07
    è´§åĪ°
    -0.06
     Wifi
    -0.06
    æŃ»äºº
    -0.06
    çĶ¨å®Į
    -0.06
    ieres
    -0.06
    äºĮåįģå¹´
    -0.06
    aukee
    -0.06
    å°ĶèĴĻ
    -0.06
    POSITIVE LOGITS
     https
    0.08
    éĺħ读åİŁæĸĩ
    0.08
    =https
    0.08
    éĵ¾æİ¥
    0.08
    https
    0.07
    raquo
    0.07
     lien
    0.07
     href
    0.07
     noreferrer
    0.07
     link
    0.07
    Activations Density 0.202%

    No Known Activations