© 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. 45779
    Prev
    Next
    INDEX
    Explanations

    suffix -itis or -ase

    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
    åIJī祥å¦ĤæĦı
    -0.08
    achts
    -0.07
    ochen
    -0.07
    onomy
    -0.07
    .Constraint
    -0.07
    ä»ĸåij½
    -0.07
    å¼ı设计
    -0.06
    inkin
    -0.06
    æ£ĢæŁ¥å·¥ä½ľ
    -0.06
    uli
    -0.06
    POSITIVE LOGITS
     weder
    0.08
    icorn
    0.07
    åį«ä¸ľ
    0.07
    enor
    0.07
    ä½Ľåħ°
    0.06
     quá»·
    0.06
    eor
    0.06
     جÙĩ
    0.06
    æѦéĻµ
    0.06
    é£ĺé£ĺ
    0.06
    Activations Density 0.005%

    No Known Activations