© 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. 23832
    Prev
    Next
    INDEX
    Explanations

    truthfulness and correctness

    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
    engi
    -0.08
    TextNode
    -0.08
    entino
    -0.08
    æĦŁè§īå¾Ī
    -0.07
    indre
    -0.07
    kes
    -0.07
    ç½ĹæĽ¼
    -0.07
    ebo
    -0.07
    boa
    -0.07
    æĸĩåĵ²
    -0.07
    POSITIVE LOGITS
    -minded
    0.09
     ones
    0.09
     ways
    0.08
    ä¹ĭ士
    0.08
    æĹłæ¯ĶçļĦ
    0.08
    ç¼ķ
    0.08
    æłĩåĩĨçļĦ
    0.08
     albeit
    0.08
    -looking
    0.07
    /non
    0.07
    Activations Density 0.118%

    No Known Activations