© 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. 61910
    Prev
    Next
    INDEX
    Explanations

    code block start

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.10
    emui
    -0.10
     domm
    -0.10
    etakkan
    -0.09
     domesti
    -0.09
     scola
    -0.09
     prenn
    -0.09
     Istitu
    -0.09
     huyn
    -0.09
    kamah
    -0.09
    POSITIVE LOGITS
    0.07
    al
    0.06
    1
    0.06
    2
    0.06
    ixe
    0.06
    4
    0.06
    §
    0.06
     ‘
    0.06
    alit
    0.05
    6
    0.05
    Activations Density 0.403%

    No Known Activations