© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25174
    Prev
    Next
    INDEX
    Explanations

    -ing / -ating / -izing / -uced / -oring

    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
    ITY
    -0.07
    ity
    -0.07
    ness
    -0.07
    cence
    -0.07
    ÑįÑį
    -0.06
    ÛĮÙĩ
    -0.06
    å®ģ
    -0.06
    ÑĮе
    -0.06
    ваниÑİ
    -0.06
    æīĭ头
    -0.06
    POSITIVE LOGITS
    orch
    0.09
    tür
    0.07
    +=(
    0.07
    轩è¾ķ
    0.07
    »
    0.07
    ating
    0.07
    lobber
    0.07
    ocking
    0.07
    潺
    0.07
    lashes
    0.07
    Activations Density 0.332%

    No Known Activations