© 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. 56660
    Prev
    Next
    INDEX
    Explanations

    representing or copying

    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
    èĩªè¡ĮæıIJä¾Ľ
    -0.07
    çªģçĦ¶åıijçİ°
    -0.06
    å¦ĩ产
    -0.06
    ä¹Ķ丹
    -0.06
    åĪĨæŀIJæĬ¥åijĬ
    -0.06
     Bord
    -0.06
    åĨħ容æıIJä¾Ľæĸ¹
    -0.06
    å¿ĥçIJĨåĩĨå¤ĩ
    -0.06
     preparations
    -0.06
    æľĢè¿ijæĽ´æĸ°
    -0.06
    POSITIVE LOGITS
     faithfully
    0.08
    å¿ł
    0.08
    ddl
    0.07
    ongen
    0.07
    æĢĿ
    0.07
     fidelity
    0.07
    äºĨåIJĹ
    0.07
    ubil
    0.07
    å¿łå®ŀ
    0.07
    Copy
    0.07
    Activations Density 0.003%

    No Known Activations