© 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. 17212
    Prev
    Next
    INDEX
    Explanations

    background of disclosure

    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
    incid
    -0.08
    梯度
    -0.08
    è°Ĩ
    -0.07
    chia
    -0.07
    .shadow
    -0.07
    atur
    -0.07
     fov
    -0.07
    .inc
    -0.07
    _RSA
    -0.07
    第äºĮç§į
    -0.07
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.07
    å¥Ĺ
    0.07
    Thought
    0.07
     Thoughts
    0.06
    æľºä¼ļ
    0.06
    Spec
    0.06
    à¸į
    0.06
    åĴĮæĢĿèĢĥ
    0.06
    äºĶèĬ±
    0.06
    squ
    0.06
    Activations Density 0.006%

    No Known Activations