© 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. 12043
    Prev
    Next
    INDEX
    Explanations

    reducing sugar, oxidation, reaction, amino

    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
    ër
    -0.08
    ä¸įæīĵ
    -0.08
    upert
    -0.08
    tox
    -0.07
    oplan
    -0.07
    nty
    -0.07
     Ãīr
    -0.07
    orton
    -0.07
    æīĩ
    -0.07
    åĬªåĬĽæĬĬ
    -0.07
    POSITIVE LOGITS
    è¿Ľè¡Įæ£Ģæµĭ
    0.08
     ability
    0.07
    æ£ĢæµĭæľºæŀĦ
    0.07
    æ£Ģæµĭæĸ¹æ³ķ
    0.07
    detect
    0.07
    æ´»æĢ§
    0.07
    活泼
    0.07
     detecting
    0.07
    çļĦæ£Ģæµĭ
    0.07
    sem
    0.07
    Activations Density 0.009%

    No Known Activations