© 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. 12874
    Prev
    Next
    INDEX
    Explanations

    location and biological/technical terms

    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
    ingt
    -0.07
    æıIJä¾ĽæĽ´åĬł
    -0.07
    缴
    -0.06
     fore
    -0.06
     Fore
    -0.06
    ÙĤÙĩ
    -0.06
    .TIM
    -0.06
    fore
    -0.06
    åıĬè¦ģæ±Ĥ
    -0.06
    ucch
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİæł¹æį®
    0.09
    encer
    0.08
    æ·ij
    0.08
     بدÙĪرÙĩ
    0.08
    ä½łåĨį
    0.07
    목
    0.07
    asher
    0.07
    åĨį说
    0.07
    enta
    0.07
    목ìĿĦ
    0.07
    Activations Density 0.015%

    No Known Activations