© 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. 64777
    Prev
    Next
    INDEX
    Explanations

    graph

    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
    çĥŃçĪ±ç¥ĸåĽ½
    -0.07
    éķ¿ç©º
    -0.06
    æ£
    -0.06
    _screen
    -0.06
    èijµèĬ±
    -0.06
    çļĦéĩı
    -0.06
    顺延
    -0.06
    /rs
    -0.06
    å¾®éĩı
    -0.06
    éĩijæ²Ļ
    -0.06
    POSITIVE LOGITS
     connectivity
    0.11
     graph
    0.11
    graph
    0.10
     adjacency
    0.10
    Vertices
    0.10
     Connectivity
    0.09
    çĶ»æ³ķ
    0.09
    /graph
    0.09
    (graph
    0.09
     network
    0.09
    Activations Density 0.120%

    No Known Activations