© 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. 43940
    Prev
    Next
    INDEX
    Explanations

    airport

    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
    igi
    -0.06
    ...
    -0.06
     gur
    -0.06
    “
    -0.06
     host
    -0.06
    venz
    -0.05
    代代
    -0.05
    ÙĦØ©
    -0.05
    çľģ
    -0.05
     mini
    -0.05
    POSITIVE LOGITS
    å®ļäºİ
    0.09
    nese
    0.08
    ransition
    0.08
    åħ·æľīè¾ĥ强çļĦ
    0.08
    çŁ¥ç½ij
    0.08
    _accepted
    0.08
     astron
    0.08
    ij¸
    0.08
    å°¼åħĭ
    0.08
    çļĪ
    0.08
    Activations Density 0.036%

    No Known Activations