© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    live, temporary, observations, maintenance, behavior

    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
    _FLUSH
    -0.08
    æ£Ħ
    -0.06
     procé
    -0.06
    uzion
    -0.06
     procedure
    -0.06
    å¼ĥ
    -0.06
     juridi
    -0.06
    .fil
    -0.06
    íĭ±
    -0.06
    å¥ĩéģĩ
    -0.06
    POSITIVE LOGITS
    常年
    0.10
    æ´»
    0.09
    临æŶ
    0.09
    常驻
    0.09
     دائÙħ
    0.09
     live
    0.09
    常æĢģåĮĸ
    0.09
    临
    0.08
     temporary
    0.08
    Temporary
    0.08
    Activations Density 0.837%

    No Known Activations