© 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. 31435
    Prev
    Next
    INDEX
    Explanations

    Lie algebra type D cluster

    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
     Bod
    -0.07
    æijĩåı·
    -0.07
    гелÑĮ
    -0.06
    设å¤ĩè¿Ľè¡Į
    -0.06
     Destin
    -0.06
     anonym
    -0.06
    ovation
    -0.06
    表éĿ¢
    -0.06
     bio
    -0.06
    oo
    -0.06
    POSITIVE LOGITS
    ç°ĩ
    0.08
    -cluster
    0.08
    ÐijÐļ
    0.08
    _cluster
    0.08
    å°Ħ
    0.07
     Crossing
    0.07
    USTER
    0.07
     khẩu
    0.07
    aggi
    0.07
    -project
    0.07
    Activations Density 0.011%

    No Known Activations