© 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. 58535
    Prev
    Next
    INDEX
    Explanations

    GUIDs and identifiers

    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
    åĬĽä½ľ
    -0.08
    rike
    -0.08
    uintptr
    -0.08
    .expect
    -0.08
    ackt
    -0.08
    主é¢ĺæĺ¯
    -0.07
    Mvc
    -0.07
    znak
    -0.07
    emps
    -0.07
    åıĸæ¶Īåħ¶
    -0.07
    POSITIVE LOGITS
    çĶŁçĶŁ
    0.07
    dea
    0.06
    ason
    0.06
    åĺ´
    0.06
    unga
    0.06
    åħ¨èº«
    0.06
    æijĩ
    0.06
    款
    0.06
     ais
    0.06
    ordon
    0.06
    Activations Density 0.006%

    No Known Activations