© 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. 26483
    Prev
    Next
    INDEX
    Explanations

    diamond and gems

    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
    éľĨ
    -0.08
    åIJĪ并
    -0.07
    æ½®
    -0.07
    åįĥ家
    -0.07
    vola
    -0.07
    èĹ
    -0.07
    anzi
    -0.07
    eward
    -0.07
    å¤§æ±Ł
    -0.07
    unno
    -0.07
    POSITIVE LOGITS
     diamond
    0.10
    åİŁçŁ³
    0.10
     crystal
    0.10
    æĻ¶ä½ĵ
    0.10
    éĩijåĪļçŁ³
    0.10
     crystals
    0.09
    å®ĿçŁ³
    0.09
    éĴ»æĪĴ
    0.09
    éĴ»çŁ³
    0.09
     diamonds
    0.09
    Activations Density 0.039%

    No Known Activations