© 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. 42133
    Prev
    Next
    INDEX
    Explanations

    equivalence and similarity

    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
    èݹ
    -0.08
    空空
    -0.08
     quais
    -0.07
    oho
    -0.07
    ockey
    -0.07
    .touch
    -0.07
     therein
    -0.07
    оÑĢÑı
    -0.07
    åĨ²åĩº
    -0.07
    _intersection
    -0.06
    POSITIVE LOGITS
     sam
    0.07
    ä¸įç®¡ä½ł
    0.07
    Plain
    0.07
     plain
    0.07
    ipsis
    0.07
    kland
    0.06
     absolu
    0.06
    à¸ģัà¸Ļà¹Ħà¸Ķà¹ī
    0.06
    åįģ足çļĦ
    0.06
    Äģv
    0.06
    Activations Density 0.002%

    No Known Activations