© 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. 51294
    Prev
    Next
    INDEX
    Explanations

    references and citations

    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
     Galler
    -0.09
    å¾Ģ
    -0.08
    Ñħло
    -0.07
    zier
    -0.07
    ä¹ħèĢĮ
    -0.06
    utsch
    -0.06
    DT
    -0.06
    extr
    -0.06
    ä»İæĹł
    -0.06
    عت
    -0.06
    POSITIVE LOGITS
    combined
    0.08
     combined
    0.08
    çĦ
    0.08
     kombini
    0.07
    æĹı群
    0.07
     Tomorrow
    0.07
    важа
    0.07
    .bs
    0.07
    &B
    0.07
     divid
    0.07
    Activations Density 0.068%

    No Known Activations