© 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. 2994
    Prev
    Next
    INDEX
    Explanations

    grammatical endings and forms

    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
    çĿģå¼Ģçľ¼çĿĽ
    -0.08
    夹å±Ĥ
    -0.07
    ceau
    -0.07
    åĮ»åѦè§Ĥå¯Ł
    -0.07
    reur
    -0.06
    reno
    -0.06
    Bins
    -0.06
    å¾ģä¿¡
    -0.06
     Fah
    -0.06
    itaire
    -0.06
    POSITIVE LOGITS
     endings
    0.09
     worn
    0.09
     forms
    0.08
     gramm
    0.08
    uffix
    0.07
    åıĺåĮĸ
    0.07
     grammar
    0.07
    Grammar
    0.07
     orth
    0.07
    /forms
    0.07
    Activations Density 0.024%

    No Known Activations