© 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. 55497
    Prev
    Next
    INDEX
    Explanations

    variable assignment or usage

    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
    ãĥ¼ãĥĦ
    -0.07
    Loader
    -0.07
    íĥĿ
    -0.07
    åºĶçĶ¨èĥ½åĬĽ
    -0.06
    ajer
    -0.06
    _loader
    -0.06
    æ±ĤçĶŁåŃĺ
    -0.06
    idium
    -0.06
    inea
    -0.06
    facet
    -0.06
    POSITIVE LOGITS
    åıĺéĩı
    0.15
    åıĺéĩıçļĦ
    0.12
     variables
    0.12
     ë³ĢìĪĺ
    0.11
     variable
    0.11
     Variables
    0.10
     variabel
    0.10
     пеÑĢемен
    0.10
    _variable
    0.09
    èµĭåĢ¼
    0.09
    Activations Density 0.519%

    No Known Activations