© 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. 7563
    Prev
    Next
    INDEX
    Explanations

    interaction and forces

    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
    çĺĢ
    -0.08
    æµģéĩıçļĦ
    -0.07
    çĶŁçIJĨåѦ
    -0.07
    ometr
    -0.07
    çĮ®è¡Ģ
    -0.07
    uctose
    -0.07
    ceg
    -0.07
    è¡Ģæµģ
    -0.07
    åĩºè´§éĩı
    -0.07
    ikian
    -0.07
    POSITIVE LOGITS
     interaction
    0.09
    Interaction
    0.08
     Interaction
    0.08
    interaction
    0.08
    entiel
    0.08
    缸äºĴä½ľçĶ¨
    0.08
     interacts
    0.07
     interacting
    0.07
     suscept
    0.07
    å¾ĹåĬĽ
    0.07
    Activations Density 0.004%

    No Known Activations