© 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. 10030
    Prev
    Next
    INDEX
    Explanations

    bounce or wall collision

    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
    è¿ģ
    -0.07
    addAll
    -0.06
    stur
    -0.06
    _constructor
    -0.06
    è®¤çľŁåģļ好
    -0.06
    StackSize
    -0.06
     remotely
    -0.06
    èººåľ¨åºĬä¸Ĭ
    -0.06
    å®ĺ
    -0.06
    Distribution
    -0.06
    POSITIVE LOGITS
     trajectory
    0.09
    åħĪåIJİ
    0.09
    è¿ŁæĹ©
    0.08
    å¿ħåħĪ
    0.08
    轨迹
    0.08
    meden
    0.08
    åħĪåIJİåľ¨
    0.08
     specular
    0.08
    å¿ħ
    0.08
    å¿ħçĦ¶ä¼ļ
    0.08
    Activations Density 0.004%

    No Known Activations