© 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. 22190
    Prev
    Next
    INDEX
    Explanations

    RUN: opt

    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
    é»
    -0.07
    emo
    -0.07
    anci
    -0.07
    çĶŁéķ¿åıijèĤ²
    -0.07
    หู
    -0.07
     ترب
    -0.07
    strup
    -0.07
    emann
    -0.07
    uria
    -0.07
    URO
    -0.06
    POSITIVE LOGITS
    å°±åģļ
    0.07
    ESE
    0.07
    istik
    0.07
    åľ¨ä½ı
    0.07
     pál
    0.07
    elix
    0.07
    俱ä¹IJéĥ¨
    0.06
    izare
    0.06
    umb
    0.06
    iced
    0.06
    Activations Density 0.001%

    No Known Activations