© 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. 4066
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by new sentence clause

    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
    tle
    -0.06
    M
    -0.06
     first
    -0.06
    Mo
    -0.06
    MZ
    -0.05
    第ä¸Ģ
    -0.05
    MO
    -0.05
     Mo
    -0.05
    Na
    -0.05
     rather
    -0.05
    POSITIVE LOGITS
    é¡¿äºĨé¡¿
    0.10
    说çĿĢ
    0.10
    说罢
    0.10
    说åĪ°è¿ĻéĩĮ
    0.09
    说å®Į
    0.09
    åģľäºĨ
    0.09
    æķĻèĤ²ä¸İ
    0.09
    merce
    0.09
    游åĪĥ
    0.08
    æĬķèµĦ管çIJĨ
    0.08
    Activations Density 0.068%

    No Known Activations