© 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. 29034
    Prev
    Next
    INDEX
    Explanations

    agencies and authorities

    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
    zk
    -0.08
    ãĤ®ãĥª
    -0.08
    -extra
    -0.07
    èĥĸèĥĸ
    -0.07
    å°½éĩıå°ij
    -0.07
    bst
    -0.07
    rip
    -0.06
    zelt
    -0.06
    hors
    -0.06
    bah
    -0.06
    POSITIVE LOGITS
    è¯ķçĤ¹å·¥ä½ľ
    0.12
    è¯ķçĤ¹
    0.09
    ä½ĵ系建设
    0.09
     pilot
    0.09
     Pilot
    0.09
    åĮºåĮº
    0.08
     pilots
    0.08
    eman
    0.08
    LOW
    0.07
    ilot
    0.07
    Activations Density 0.145%

    No Known Activations