© 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. 15696
    Prev
    Next
    INDEX
    Explanations

    words ending in ing

    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
    ulu
    -0.07
    æ¯Ĺ
    -0.06
    ORA
    -0.06
     yourself
    -0.06
    å°Ķ
    -0.06
    å¿ĥèĤº
    -0.06
    åĪĴ
    -0.06
    ceu
    -0.06
    ISH
    -0.06
    _regex
    -0.06
    POSITIVE LOGITS
    æ¯Ķè¾ĥæľī
    0.08
    æ¯Ķè¾ĥå¤ļ
    0.08
    alse
    0.08
    оÑģÑĮ
    0.08
    Ñĩей
    0.08
    éªĭ
    0.08
    neh
    0.08
    æĸ°åįİ社记èĢħ
    0.08
    मà¥įम
    0.08
    ä»İæĿ¥ä¸į
    0.08
    Activations Density 0.020%

    No Known Activations