© 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. 41630
    Prev
    Next
    INDEX
    Explanations

    objects, destination, check, ascending, replicate, fibers

    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
    æĶ¾çĿĢ
    -0.07
    arz
    -0.07
    å®Īä½ı
    -0.07
    -regexp
    -0.07
     Pob
    -0.07
    大水
    -0.07
    æıIJä¾Ľèī¯å¥½çļĦ
    -0.07
    èĥľ
    -0.06
    Alive
    -0.06
    å·¥å§Ķ
    -0.06
    POSITIVE LOGITS
    ä¸įåĮħæĭ¬
    0.08
     нÑĥлÑı
    0.07
    èµ·çĤ¹
    0.07
    æĹłåīį
    0.07
    åĮħæĭ¬
    0.07
    ozilla
    0.07
     zero
    0.07
     Including
    0.07
    haber
    0.07
    unger
    0.07
    Activations Density 0.029%

    No Known Activations