© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20624
    Prev
    Next
    INDEX
    Explanations

    adjacent

    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
    fully
    -0.11
    æł·çļĦ
    -0.09
    aum
    -0.09
    vell
    -0.08
    iest
    -0.08
    eringen
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    ccion
    -0.08
    iness
    -0.08
    eri
    -0.08
    POSITIVE LOGITS
    èĢĮåĿIJ
    0.09
     ká»ģ
    0.09
    acent
    0.08
    ly
    0.08
    oint
    0.07
    stående
    0.07
    icts
    0.07
     дÑĢÑĥг
    0.07
    áĥĿáĥij
    0.07
    ron
    0.07
    Activations Density 0.010%

    No Known Activations