© 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. 38641
    Prev
    Next
    INDEX
    Explanations

    variable assignments with `=`

    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
    ibel
    -0.07
    achi
    -0.06
    ambul
    -0.06
    erver
    -0.06
    ç½ķ
    -0.06
    ×Ļ×Ŀ
    -0.06
    ä¸įåĮħæĭ¬
    -0.06
    aml
    -0.06
    ανά
    -0.06
    åĤ»çĵľ
    -0.06
    POSITIVE LOGITS
    -Sah
    0.08
     relent
    0.08
    åİ»çľĭ
    0.07
    erial
    0.07
    rotch
    0.07
    rok
    0.07
     gerais
    0.07
     ül
    0.07
    åĬªåĬĽåİ»
    0.07
    pillar
    0.07
    Activations Density 0.001%

    No Known Activations