© 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. 49028
    Prev
    Next
    INDEX
    Explanations

    must, other clients, writing

    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
    èĥĥåı£
    -0.09
    ìĤ¬ìłĦ
    -0.08
    ripper
    -0.08
     contractu
    -0.08
    scaling
    -0.08
    ÑħаниÑı
    -0.08
    developers
    -0.08
    edeut
    -0.08
    åĬ¨è¾Ħ
    -0.08
     ë©ĭ
    -0.08
    POSITIVE LOGITS
    å°Ĩèĩªå·±
    0.08
    çŁ¥éģĵèĩªå·±çļĦ
    0.08
    -
    0.08
    使èĩªå·±
    0.07
    åĴĮèĩªå·±
    0.07
    对èĩªå·±
    0.07
    让èĩªå·±
    0.07
     ìŀIJìĭłìĿ´
    0.06
    åıijçİ°èĩªå·±
    0.06
    å¤ļäºİ
    0.06
    Activations Density 0.001%

    No Known Activations