© 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. 26451
    Prev
    Next
    INDEX
    Explanations

    longest label

    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
    JET
    -0.08
    æłĹ
    -0.08
    Jvm
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    ноÑĢа
    -0.07
    lade
    -0.07
    lyph
    -0.07
    orts
    -0.07
    åıĹè¿ĩ
    -0.06
    (CType
    -0.06
    POSITIVE LOGITS
    è¿ĺçĶ¨
    0.08
     saja
    0.08
     دÛĮگرÛĮ
    0.08
    è¿ĺåĮħæĭ¬
    0.07
    åħ·ä½ĵçļĦ
    0.07
    ä¹Łè¡Į
    0.07
    çļĦåħ¶ä»ĸ
    0.07
    çļĦ人è¿ĺ
    0.07
    ÅŁt
    0.07
    åħ·ä½ĵæݪæĸ½
    0.07
    Activations Density 0.007%

    No Known Activations