© 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. 14379
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    باب
    -0.08
     ggf
    -0.07
    anners
    -0.07
    orar
    -0.07
    >No
    -0.07
    éģ¨
    -0.07
    iega
    -0.07
    è¿ijæľŁçļĦ
    -0.07
    unar
    -0.07
    asca
    -0.07
    POSITIVE LOGITS
    ly
    0.07
     parts
    0.07
     paddingTop
    0.06
     renc
    0.06
    è¾¾æĭī
    0.06
    dah
    0.06
    ovich
    0.06
    è¿Ļ个æķ°åŃĹ
    0.06
    .dat
    0.06
    uas
    0.06
    Activations Density 0.231%

    No Known Activations