© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14792
    Prev
    Next
    INDEX
    Explanations

    sentence structure and phrasing

    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
    éļ¾å¿ĺ
    -0.08
    tolist
    -0.08
    æ¨ĭ
    -0.07
    erged
    -0.07
    æŁ¥
    -0.07
    åıĪä½ķ
    -0.07
    æĭĽæłĩç½ij
    -0.07
     prelimin
    -0.07
    _hint
    -0.07
    òi
    -0.07
    POSITIVE LOGITS
    è¯ķåĽ¾
    0.09
    è¿ĩ度çļĦ
    0.08
     Attempt
    0.08
    Attempting
    0.08
     ph
    0.08
    alin
    0.07
     attempts
    0.07
     Attempts
    0.07
    試åľĸ
    0.07
     falsely
    0.07
    Activations Density 0.011%

    No Known Activations