© 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. 44939
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    enal
    -0.08
    ingat
    -0.07
    ode
    -0.07
    æĪı
    -0.07
    arde
    -0.07
    详ç»Ĩä»ĭç»į
    -0.07
    å°±æĢķ
    -0.07
    esse
    -0.07
    rief
    -0.07
     Prest
    -0.07
    POSITIVE LOGITS
    igli
    0.06
     huh
    0.06
    ÙĨا
    0.06
    tio
    0.06
    åįİé¾Ļ
    0.06
    emper
    0.06
    jes
    0.06
    ä¹Łå°±ä¸į
    0.06
    æĩĤäºĨ
    0.06
     Ow
    0.06
    Activations Density 0.041%

    No Known Activations