© 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. 26204
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    rike
    -0.10
    宣读äºĨ
    -0.08
    parseFloat
    -0.08
    è¿ĻæĶ¯
    -0.08
    çħľ
    -0.08
    çī¹å°Ķ
    -0.08
    ayed
    -0.08
    ×ķ×£
    -0.08
    é½IJé½IJ
    -0.08
    ague
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģ§ãģ«
    0.07
    hart
    0.06
    èĩ³ä»Ĭ
    0.06
    è¦ģæ±Ĥåľ¨
    0.06
     prime
    0.06
    ãģ¾ãģ§ãģ®
    0.06
     solver
    0.06
    tib
    0.06
     famously
    0.06
    解çŃĶ
    0.06
    Activations Density 0.027%

    No Known Activations