© 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. 22159
    Prev
    Next
    INDEX
    Explanations

    math tokens and programming concepts

    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
    .binding
    -0.06
    ou
    -0.06
    arend
    -0.05
    åį´è¦ģ
    -0.05
    adura
    -0.05
    ig
    -0.05
    legate
    -0.05
    ä½Ĩæĺ¯æ²¡æľī
    -0.05
    ehrt
    -0.05
    eh
    -0.05
    POSITIVE LOGITS
    åĨįæ·»
    0.09
    æĻı
    0.09
    ັ
    0.08
    volver
    0.08
    zkod
    0.08
    stä
    0.08
    mlink
    0.08
    isse
    0.08
    лÑĸй
    0.08
    AZE
    0.07
    Activations Density 0.008%

    No Known Activations