© 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. 11199
    Prev
    Next
    INDEX
    Explanations

    mm measurements

    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
    åħī顾
    -0.08
    çº
    -0.06
    archy
    -0.06
    åĴĮçĽijçĿ£
    -0.06
     NYT
    -0.06
    ä¸įåıĬ
    -0.06
     correctly
    -0.06
    agian
    -0.06
    æĭīæī¯
    -0.05
     contr
    -0.05
    POSITIVE LOGITS
    sizes
    0.09
     sizes
    0.09
    bolos
    0.08
     comfor
    0.08
    æ¨Ļæºĸ
    0.08
    åıĬ以ä¸ĭ
    0.08
    standard
    0.08
    obsolete
    0.08
     reloadData
    0.08
    çŃīç³»åĪĹ
    0.08
    Activations Density 0.148%

    No Known Activations