© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11756
    Prev
    Next
    INDEX
    Explanations

    XML/HTML/code delimiters

    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
    æĢİä¹ĪåĬŀåij¢
    -0.08
    çĶĺ
    -0.07
    幡
    -0.07
    äºİå¿ĥ
    -0.06
    gem
    -0.06
    gie
    -0.06
    undy
    -0.06
    loor
    -0.06
    ksi
    -0.06
    .googleapis
    -0.06
    POSITIVE LOGITS
    cls
    0.08
    æĸ°çĶŁçļĦ
    0.08
    rolet
    0.08
    é«ĺéĩĩ
    0.07
    yii
    0.07
    大åIJĮ
    0.07
    born
    0.07
    ä¸Ģè¯ķ
    0.07
    ask
    0.07
    æIJ
    0.07
    Activations Density 0.940%

    No Known Activations