© 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. 46703
    Prev
    Next
    INDEX
    Explanations

    Prime Minister and cabinet

    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
    ģ
    -0.08
    ocity
    -0.08
    keh
    -0.08
    hto
    -0.08
    awe
    -0.08
    åī¯çIJĨäºĭéķ¿
    -0.07
    abouts
    -0.07
     juridi
    -0.07
    ake
    -0.07
     بÙĨدÛĮ
    -0.07
    POSITIVE LOGITS
    åºľ
    0.10
    åºľçļĦ
    0.08
    è¡ĮæĶ¿
    0.07
    chef
    0.07
    -exec
    0.07
     ministries
    0.07
    大èĩ£
    0.07
    åĨħéĺģ
    0.07
    è¡ĮæĶ¿æľºåħ³
    0.07
    åĽ½åħ¬
    0.07
    Activations Density 0.089%

    No Known Activations