© 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. 47329
    Prev
    Next
    INDEX
    Explanations

    connected and rooted

    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
     lượt
    -0.08
    arga
    -0.07
    aceous
    -0.07
    ffer
    -0.07
    áĢ¸
    -0.07
     vá»Ŀi
    -0.06
    odelist
    -0.06
    awning
    -0.06
    awatan
    -0.06
    çIJ¦
    -0.06
    POSITIVE LOGITS
    æīİæł¹
    0.11
    ä¸į稳
    0.10
    éĶļ
    0.10
     firmly
    0.10
     Anch
    0.10
    çĶŁæł¹
    0.09
    ä¸įä½ı
    0.09
     anch
    0.09
     anchors
    0.09
    åĿļå®ŀ
    0.09
    Activations Density 0.042%

    No Known Activations