© 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. 61975
    Prev
    Next
    INDEX
    Explanations

    numbers close to zero

    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
    ovia
    -0.08
    ovem
    -0.08
    mÄĽ
    -0.08
    zelfde
    -0.08
    ovÄĽ
    -0.08
    breaker
    -0.08
    à¥į
    -0.08
    à¸Ħà¹Į
    -0.07
    hti
    -0.07
     keras
    -0.07
    POSITIVE LOGITS
    ness
    0.10
    ature
    0.08
    íŀĪ
    0.08
    æĹłéĹ»
    0.08
    abouts
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    aghan
    0.07
    owing
    0.07
    ish
    0.07
    obic
    0.07
    Activations Density 0.016%

    No Known Activations