© 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. 28481
    Prev
    Next
    INDEX
    Explanations

    alkoxy group

    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
    çľ¼å¸ĺ
    -0.06
    inci
    -0.06
    zug
    -0.06
     ame
    -0.06
     modal
    -0.06
    modal
    -0.06
    ç§ij室
    -0.06
    end
    -0.05
    osity
    -0.05
    ارة
    -0.05
    POSITIVE LOGITS
    tober
    0.11
    檻
    0.09
    stry
    0.09
    urator
    0.09
    æ§Ľ
    0.09
    ÑĢанже
    0.09
    ehm
    0.09
    éħİ
    0.09
    窯
    0.09
    portun
    0.08
    Activations Density 0.008%

    No Known Activations