© 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. 57643
    Prev
    Next
    INDEX
    Explanations

    foreach, alternate, third, known

    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
    arga
    -0.08
    齡
    -0.07
    upy
    -0.07
    inger
    -0.06
    полÑı
    -0.06
    urb
    -0.06
    èį
    -0.06
    ype
    -0.06
    argas
    -0.06
    pone
    -0.06
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.08
    ONS
    0.08
    baum
    0.07
    æ¹ĸ滨
    0.07
    å±ħæĺĵ
    0.07
    æī¹
    0.07
    ')"
    0.07
    类似çļĦ
    0.07
    imilar
    0.07
    Ñħ
    0.07
    Activations Density 0.044%

    No Known Activations