© 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. 40967
    Prev
    Next
    INDEX
    Explanations

    post navigation

    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
    atsu
    -0.07
    oku
    -0.06
    uga
    -0.06
    ukai
    -0.06
    NA
    -0.06
    Num
    -0.06
    oar
    -0.06
    赫çĦ¶
    -0.06
    Counts
    -0.06
    ÙĪاÙĨ
    -0.06
    POSITIVE LOGITS
    ieven
    0.08
     ._
    0.08
    asma
    0.08
    phu
    0.08
    ILog
    0.07
    вÑĢа
    0.07
    è¤
    0.07
    رÙĬÙĤ
    0.07
    .appspot
    0.07
    çıŃçļĦ
    0.07
    Activations Density 0.002%

    No Known Activations