© 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. 4542
    Prev
    Next
    INDEX
    Explanations

    decomposition or breakdown

    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
    æĪijçļĦæĶ¶èĹı
    -0.07
    æ¼ĶçļĦ
    -0.07
    èĮ«
    -0.07
    STA
    -0.07
    IAS
    -0.07
    finity
    -0.07
    æıı
    -0.07
    ots
    -0.06
    cntl
    -0.06
    纶
    -0.06
    POSITIVE LOGITS
    解ä½ĵ
    0.12
     containing
    0.11
     contenant
    0.10
     decom
    0.10
     Decom
    0.10
    åĪĨ解
    0.09
     chứa
    0.09
     dissoci
    0.09
     decomposition
    0.09
    contains
    0.09
    Activations Density 0.068%

    No Known Activations