© 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. 31091
    Prev
    Next
    INDEX
    Explanations

    strip domains and geographic directions

    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
    天éķ¿
    -0.08
    鸣åĸĩåıŃ
    -0.08
    illance
    -0.08
    дав
    -0.07
     Barrel
    -0.07
    ä¸Ģèµ·çİ©
    -0.07
     Laurea
    -0.07
    å¯Įè´µ
    -0.07
    odos
    -0.07
    /manual
    -0.07
    POSITIVE LOGITS
    èģ
    0.08
     horizont
    0.07
    ws
    0.07
    ilder
    0.07
    好æĸĩ
    0.06
     Moy
    0.06
    帯
    0.06
     dank
    0.06
    çŃij
    0.06
     ide
    0.06
    Activations Density 0.002%

    No Known Activations