© 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. 50645
    Prev
    Next
    INDEX
    Explanations

    Japanese text and English endings

    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
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.11
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    -0.08
    zza
    -0.08
    ãĤĤãģĹãĤĮ
    -0.08
    ارا
    -0.07
    ullets
    -0.07
    ãģ£ãģ¦ãģĦãģ¾ãģĹãģŁ
    -0.07
    leness
    -0.07
    ãģĹãģ¦ãģĦãģŁãģłãģij
    -0.07
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    -0.07
    POSITIVE LOGITS
    ing
    0.08
    ed
    0.08
    ãģ¹ãģį
    0.07
    çĿĢçļĦ
    0.07
    è¿ĩçļĦ
    0.07
    äºĨçļĦ
    0.07
    able
    0.07
    çĿĢ
    0.07
    çļĦæĺ¯
    0.07
    è¦ģæ±ĤçļĦ
    0.07
    Activations Density 0.011%

    No Known Activations