© 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. 43547
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by "but"

    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
    구ìļĶ
    -0.08
    åľ¨ä¸įåIJĮçļĦ
    -0.08
    çĶ±ä¼ģä¸ļ
    -0.08
     Muda
    -0.08
     Peña
    -0.07
    assar
    -0.07
    æĥķ
    -0.07
    ãĥ³ãĤ¹
    -0.07
     somehow
    -0.07
    aptcha
    -0.07
    POSITIVE LOGITS
    iero
    0.07
    isco
    0.07
     referenced
    0.07
    uest
    0.06
    ستاÙĨ
    0.06
    æĪijåİ»
    0.06
    qués
    0.06
    оÑģÑĤей
    0.06
    ries
    0.06
    eci
    0.06
    Activations Density 0.005%

    No Known Activations