© 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. 51103
    Prev
    Next
    INDEX
    Explanations

    reacts with reaction

    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
    çī¹åĭĴ
    -0.08
     remis
    -0.08
     unlink
    -0.08
    OnError
    -0.07
    ebra
    -0.07
     Æ°á»Ľc
    -0.07
    unlink
    -0.07
    âm
    -0.07
    èµĦ
    -0.07
    éĢĢæį¢
    -0.06
    POSITIVE LOGITS
     interaction
    0.08
     formation
    0.08
    åį³åı¯å®ĮæĪIJ
    0.08
    åĬĽå¼º
    0.08
     productive
    0.08
    formation
    0.08
     prefer
    0.07
    inov
    0.07
    åĪ°åºķ
    0.07
     followed
    0.07
    Activations Density 0.014%

    No Known Activations