© 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. 60806
    Prev
    Next
    INDEX
    Explanations

    air rise and flow

    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
    uede
    -0.08
    ãģ°
    -0.07
    мила
    -0.07
     shredd
    -0.07
    iena
    -0.07
    izons
    -0.07
    uras
    -0.07
    丢äºĨ
    -0.07
     slashes
    -0.07
    å¾Ģåīį
    -0.06
    POSITIVE LOGITS
     buoy
    0.11
     vertical
    0.08
     vertically
    0.08
    温差
    0.08
     spontan
    0.08
    éĩįåĬĽ
    0.08
    Bu
    0.08
    å±Ģéĥ¨çļĦ
    0.08
     locally
    0.08
     gravitational
    0.08
    Activations Density 0.004%

    No Known Activations