© 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. 48878
    Prev
    Next
    INDEX
    Explanations

    vertical UITableView struct Emp strategic Hz

    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
    ook
    -0.07
    adero
    -0.07
    =sc
    -0.07
    ÑĩÑĥ
    -0.07
    cek
    -0.07
    cop
    -0.07
    éĻIJ度
    -0.07
    hyl
    -0.07
     воÑģк
    -0.07
    nut
    -0.06
    POSITIVE LOGITS
    å®ıè§Ĥ
    0.11
    æħ¢
    0.11
     macro
    0.10
    macro
    0.09
    å®ı
    0.09
     мак
    0.08
     coarse
    0.08
     Macro
    0.08
    -meta
    0.08
    å¾Īæħ¢
    0.08
    Activations Density 0.151%

    No Known Activations