© 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. 64966
    Prev
    Next
    INDEX
    Explanations

    depends on variation

    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
    enza
    -0.07
    leun
    -0.07
    _ordered
    -0.07
    oph
    -0.07
    æľīéģĵ
    -0.06
    yani
    -0.06
    otu
    -0.06
    çĤŃ
    -0.06
    mid
    -0.06
    åį³æĹ¥
    -0.06
    POSITIVE LOGITS
    åıĸåĨ³äºİ
    0.26
     depends
    0.23
     завиÑģиÑĤ
    0.20
    depends
    0.20
     depende
    0.19
     depend
    0.19
     Depends
    0.18
     depended
    0.18
    åıĸåĨ³
    0.18
     depending
    0.18
    Activations Density 0.271%

    No Known Activations