© 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. 46746
    Prev
    Next
    INDEX
    Explanations

    sequences of control 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
    away
    -0.06
    ii
    -0.06
    iad
    -0.06
    æĪ®
    -0.05
    å°ıçļĦ
    -0.05
    ö
    -0.05
    æĺ¾ç¤º
    -0.05
    å°ıç¼ĸ
    -0.05
     lim
    -0.05
    ä¸¥æł¼
    -0.05
    POSITIVE LOGITS
    eret
    0.09
    .nr
    0.09
    zilla
    0.09
    araf
    0.09
    erne
    0.08
    -divider
    0.08
    اÙĨات
    0.08
     }</
    0.08
    idelberg
    0.08
    bane
    0.08
    Activations Density 0.007%

    No Known Activations