© 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. 47264
    Prev
    Next
    INDEX
    Explanations

    verbs in questions

    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
    褶
    -0.07
    è°ļ
    -0.06
    icious
    -0.06
    à¹ģà¸Ĺà¹ī
    -0.06
    zar
    -0.06
    Wildcard
    -0.06
    缸åħ³æĸĩç«ł
    -0.06
    èĩ³ä¸Ĭ
    -0.06
    çļĦå°ıç¼ĸ
    -0.06
    arde
    -0.06
    POSITIVE LOGITS
    agak
    0.08
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.08
    /get
    0.08
    /connect
    0.08
    /close
    0.08
    /reg
    0.08
    /delete
    0.07
    ãĤ¨ãĤ¹ãĥĪ
    0.07
    ellem
    0.07
    /create
    0.07
    Activations Density 0.062%

    No Known Activations