© 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. 56823
    Prev
    Next
    INDEX
    Explanations

    fission yeast fragmentation

    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
     Peel
    -0.08
     rabat
    -0.08
    .qual
    -0.08
    tesis
    -0.08
    outing
    -0.07
    outed
    -0.07
    举åįĩ
    -0.07
    retta
    -0.07
    .freeze
    -0.07
    å·¡è§Ĩåijĺ
    -0.07
    POSITIVE LOGITS
     random
    0.08
     fragments
    0.07
     triggered
    0.07
    éļıæľº
    0.07
     Random
    0.07
     tramp
    0.07
     spontan
    0.07
     randomly
    0.07
    erb
    0.07
    richter
    0.07
    Activations Density 0.001%

    No Known Activations