© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22685
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with x and n

    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
    ï¸İ
    -0.07
    æ´¼
    -0.06
    èĵī
    -0.06
     (<
    -0.06
     possibility
    -0.06
    âī¤
    -0.06
    å°ıéĽª
    -0.06
    å©¿
    -0.06
    å°Ŀ
    -0.06
    å°ı鼨
    -0.06
    POSITIVE LOGITS
    µ¬
    0.08
    rave
    0.08
    OBO
    0.08
    uge
    0.07
    è¿ľè¶ħ
    0.07
    çļĦ巨大
    0.07
    aldi
    0.07
    以大
    0.07
    untas
    0.07
    uridad
    0.07
    Activations Density 0.007%

    No Known Activations