© 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. 16541
    Prev
    Next
    INDEX
    Explanations

    price amounts

    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
    æĬĬå·¥ä½ľ
    -0.08
     Variety
    -0.08
    天é¾Ļ
    -0.07
    çļĦ太éĺ³
    -0.07
    illac
    -0.07
    å®Ľèĭ¥
    -0.07
    æĺ¯äººçĶŁ
    -0.07
    æĸ°åįİ社记èĢħ
    -0.07
    å¤§åľ£
    -0.07
    ifact
    -0.07
    POSITIVE LOGITS
     volant
    0.07
     scont
    0.07
     Trib
    0.07
    criptors
    0.07
    çļ±
    0.07
     envis
    0.06
    sonian
    0.06
    çħ¦
    0.06
    çŃī大
    0.06
    大æ´ĭ
    0.06
    Activations Density 0.060%

    No Known Activations