© 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. 20940
    Prev
    Next
    INDEX
    Explanations

    molecular dynamics or physics

    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
    kod
    -0.08
     relève
    -0.08
    nage
    -0.08
    éĶĢ
    -0.07
     despacho
    -0.07
    pson
    -0.07
    åľ¨å·¥ä½ľä¸Ń
    -0.07
    ilog
    -0.07
    ingham
    -0.07
    olic
    -0.07
    POSITIVE LOGITS
    ybrid
    0.08
     bonding
    0.07
     Aufbau
    0.07
     Oxygen
    0.07
    -shared
    0.07
    çĩĥæĸĻçĶµæ±ł
    0.07
    ambul
    0.07
    aney
    0.07
    çļĦçĶµåŃIJ
    0.07
    /ion
    0.06
    Activations Density 0.001%

    No Known Activations