© 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. 13944
    Prev
    Next
    INDEX
    Explanations

    seeking to find something

    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
    ities
    -0.08
    almente
    -0.08
    atura
    -0.08
    adat
    -0.08
    รà¸Ń
    -0.07
    alamat
    -0.07
    stående
    -0.07
    ifat
    -0.07
    wn
    -0.07
    buat
    -0.07
    POSITIVE LOGITS
    åĪ°çļĦ
    0.09
     refuge
    0.09
    å·²ä¹ħçļĦ
    0.09
     clarification
    0.08
    AnimationFrame
    0.08
    ed
    0.08
    ุ
    0.08
    ä¸įåĪ°çļĦ
    0.08
    lessly
    0.08
     ÙĪراء
    0.08
    Activations Density 0.045%

    No Known Activations