© 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. 17958
    Prev
    Next
    INDEX
    Explanations

    derivatives and powers

    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
    letcher
    -0.08
    _reload
    -0.07
    åºŁçº¸
    -0.07
    é»ijå¤ľ
    -0.07
    ician
    -0.07
    OfType
    -0.07
    æĸ°åħī
    -0.07
    åķ¡
    -0.07
    ahari
    -0.07
    stown
    -0.07
    POSITIVE LOGITS
    åĵĦ
    0.07
     Afr
    0.07
    ä¼¼éĶ¦
    0.06
    adius
    0.06
    æľĢåIJİä¸Ģ次
    0.06
    èŀ
    0.06
    acion
    0.06
    ertime
    0.06
     developmental
    0.06
    .Serializable
    0.06
    Activations Density 0.010%

    No Known Activations