© 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. 14989
    Prev
    Next
    INDEX
    Explanations

    sports and activities

    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
    æĮ¯åįİ
    -0.08
    æĢ§çĹħ
    -0.07
    جاÙħ
    -0.07
    Ñģпали
    -0.07
    IER
    -0.07
    家åºĦ
    -0.07
    ase
    -0.07
    elah
    -0.07
    豪æĿ°
    -0.07
    AndView
    -0.07
    POSITIVE LOGITS
    è¦ģä¿ĿæĮģ
    0.08
    riba
    0.08
    vangen
    0.06
    antu
    0.06
    еÑģÑĤва
    0.06
    âĸ½
    0.06
    artos
    0.06
    京
    0.06
    increments
    0.06
    holes
    0.06
    Activations Density 0.011%

    No Known Activations