© 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. 58193
    Prev
    Next
    INDEX
    Explanations

    formation of

    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
    andro
    -0.08
    faction
    -0.08
    ombine
    -0.08
    ÑıÑĤи
    -0.08
    rome
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    aporte
    -0.08
    æ³ķéŨ
    -0.07
    หมาย
    -0.07
    opia
    -0.07
    POSITIVE LOGITS
    ulates
    0.10
    ulating
    0.10
    ulario
    0.09
    ãģ¹ãģı
    0.08
    ül
    0.08
    UTURE
    0.08
    OrUpdate
    0.08
    oul
    0.08
    sted
    0.07
    lessly
    0.07
    Activations Density 0.060%

    No Known Activations