© 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. 17832
    Prev
    Next
    INDEX
    Explanations

    length contraction, relativistic mass, activation

    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
    .removeFrom
    -0.08
    umon
    -0.07
    iep
    -0.07
    vet
    -0.07
    igel
    -0.07
    æīĢ欲è¨Ģ
    -0.07
    èī¯å¥½çļĦåŁºç¡Ģ
    -0.07
    witter
    -0.07
    ç½Ħ
    -0.07
    å¤ļ空
    -0.07
    POSITIVE LOGITS
     factor
    0.08
    åĽłåŃIJ
    0.08
    æķĪ
    0.07
    åĽłç´ł
    0.07
    /ext
    0.07
    åĽłç´łå½±åĵį
    0.07
    /we
    0.07
     scher
    0.07
     Factor
    0.07
    _apps
    0.07
    Activations Density 0.003%

    No Known Activations