© 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. 14641
    Prev
    Next
    INDEX
    Explanations

    numbers followed by rounding or specific characters

    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
    ÙĪاÙĦÙĬ
    -0.08
    .setLayout
    -0.07
    女婿
    -0.07
    Åĵurs
    -0.07
    >ID
    -0.07
    ×Ļר×ķת
    -0.07
    èĢIJå¿ĥçļĦ
    -0.07
    atórios
    -0.07
    pack
    -0.07
    Padding
    -0.07
    POSITIVE LOGITS
    0.08
    ä¹İ
    0.07
     thro
    0.07
     freaking
    0.07
    åľĪ
    0.06
    åı²çļĦ
    0.06
    à¤Ĥस
    0.06
    igans
    0.06
    awal
    0.06
    ean
    0.06
    Activations Density 0.034%

    No Known Activations