© 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. 43321
    Prev
    Next
    INDEX
    Explanations

    for/from followed by specific word types

    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
    غÙĦ
    -0.07
     Coro
    -0.06
    峪
    -0.06
    tiz
    -0.06
    就象
    -0.06
    utus
    -0.06
    esak
    -0.06
     Electr
    -0.06
    æĽ´åĬłæĸ¹ä¾¿
    -0.06
    åı¸æ³ķé£İéĻ©
    -0.06
    POSITIVE LOGITS
     modern
    0.08
     kebanyakan
    0.08
    modern
    0.08
    hle
    0.07
    اÛĮ
    0.07
    æѤ类
    0.07
     данного
    0.07
    çļĦä¸Ģç±»
    0.07
     such
    0.06
    ib
    0.06
    Activations Density 0.109%

    No Known Activations