© 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. 40206
    Prev
    Next
    INDEX
    Explanations

    message punctuation

    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
     Alternate
    -0.07
    opolitan
    -0.07
    èѦéĴŁ
    -0.07
    zak
    -0.07
    zna
    -0.07
    uits
    -0.07
    纨
    -0.07
    æij¸ç´¢
    -0.07
    notice
    -0.07
    Broker
    -0.07
    POSITIVE LOGITS
    æĮīè¦ģæ±Ĥ
    0.07
     flair
    0.07
    ØŃÙĬ
    0.07
    gere
    0.07
     extrav
    0.07
    庸
    0.06
    åĭĩèĢħ
    0.06
     extr
    0.06
    åįıåķĨ解åĨ³
    0.06
    æŀī
    0.06
    Activations Density 0.008%

    No Known Activations