© 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. 47930
    Prev
    Next
    INDEX
    Explanations

    problem where, known that, merit 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
    ebbe
    -0.08
    eba
    -0.08
    odox
    -0.07
    èĬ³
    -0.07
    anut
    -0.07
     Conc
    -0.06
    δÏĮ
    -0.06
    .meta
    -0.06
    irut
    -0.06
     Poli
    -0.06
    POSITIVE LOGITS
     incid
    0.08
    欢è¿İæĤ¨çļĦ
    0.07
    ủa
    0.07
    ìĽ
    0.07
     renvo
    0.06
    arco
    0.06
    è¾¾
    0.06
    åįĥåįĥ
    0.06
    ctions
    0.06
    æīİ
    0.06
    Activations Density 0.145%

    No Known Activations