© 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. 7577
    Prev
    Next
    INDEX
    Explanations

    derived from or plural forms of words

    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
    åIJİèĩ³
    -0.07
    unta
    -0.07
     staged
    -0.07
    äºĭåħĪ
    -0.07
    (description
    -0.07
    ijan
    -0.07
    van
    -0.06
    etas
    -0.06
    undefined
    -0.06
    æĺİç¡®æĮĩåĩº
    -0.06
    POSITIVE LOGITS
     spelling
    0.11
     spelled
    0.10
    uffix
    0.10
    Prefix
    0.10
     spell
    0.10
     Prefix
    0.10
    Derived
    0.09
     cogn
    0.09
    prefix
    0.09
    è¡įçĶŁ
    0.09
    Activations Density 0.151%

    No Known Activations