© 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. 48087
    Prev
    Next
    INDEX
    Explanations

    sentence starters after punctuation

    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
    å°Ķå¾·
    -0.08
    请çĻ»å½ķ
    -0.08
    磼
    -0.07
    à¹Ģà¸ļืà¹īà¸Ńà¸ĩ
    -0.07
    inales
    -0.07
    æĥŃ
    -0.07
     (...
    -0.07
    ongyang
    -0.07
    çĮĽè¿Ľ
    -0.07
    δε
    -0.07
    POSITIVE LOGITS
    enf
    0.06
     Zir
    0.06
    æī£
    0.06
    åĻ¢
    0.06
    è
    0.06
    çĥŁéĽ¨
    0.06
    lea
    0.06
    .fun
    0.06
    pter
    0.06
    ply
    0.06
    Activations Density 0.009%

    No Known Activations