© 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. 9615
    Prev
    Next
    INDEX
    Explanations

    network topology and networks

    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
    为åĩĨ
    -0.08
     Miet
    -0.07
     höh
    -0.06
    angat
    -0.06
     preparations
    -0.06
    ãĥķãĤ¡ãĥŁ
    -0.06
    åºķæ°Ķ
    -0.06
    obie
    -0.06
    åľŃ
    -0.06
    èIJ½æĹ¥
    -0.06
    POSITIVE LOGITS
     networks
    0.11
     network
    0.11
     connectivity
    0.10
    ç½ij绾çļĦ
    0.10
    /network
    0.10
    ç¨Ģçĸı
    0.10
    network
    0.10
     Networks
    0.10
     nodes
    0.09
    -network
    0.09
    Activations Density 0.073%

    No Known Activations