© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10826
    Prev
    Next
    INDEX
    Explanations

    effortless or simple tasks

    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
    isca
    -0.08
    igd
    -0.07
    okus
    -0.07
    pire
    -0.07
    .IsValid
    -0.07
    postgres
    -0.07
    ÙİعÙĴ
    -0.07
    arian
    -0.07
    baugh
    -0.07
    unami
    -0.07
    POSITIVE LOGITS
    è¿Ļä¹Īç®Ģåįķ
    0.10
     straightforward
    0.09
    easy
    0.09
     easy
    0.08
    ivial
    0.08
     fácil
    0.08
    ington
    0.07
    å¾Ī容æĺĵ
    0.07
    å¯ĵ
    0.07
    /simple
    0.07
    Activations Density 0.062%

    No Known Activations