© 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. 39619
    Prev
    Next
    INDEX
    Explanations

    numbers followed by letters

    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
    åijķ
    -0.07
    èĤºæ°Ķ
    -0.07
    èģĶéĺ²èģĶæݧ
    -0.07
    è¿ĻäºĽéĹ®é¢ĺ
    -0.07
    é¢ijçİĩ
    -0.07
    é¢ij
    -0.07
    çļĦé¢ijçİĩ
    -0.07
    å¾Īå¤ļ人çļĦ
    -0.06
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.06
    anga
    -0.06
    POSITIVE LOGITS
    £
    0.08
    udos
    0.07
    orium
    0.06
    UNS
    0.06
     soucis
    0.06
    rå
    0.06
    çĤ¹åĩ»æŁ¥çľĭ
    0.06
    års
    0.06
    ÅŁtır
    0.06
    rieb
    0.06
    Activations Density 0.032%

    No Known Activations