© 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. 39454
    Prev
    Next
    INDEX
    Explanations

    HTML list items or code blocks

    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
    icum
    -0.07
    ique
    -0.07
    ом
    -0.06
    p
    -0.06
    er
    -0.06
    odo
    -0.06
    çļĦå°±æĺ¯
    -0.06
    举è¡Ĺ
    -0.06
    inge
    -0.06
    ë§ŀ
    -0.06
    POSITIVE LOGITS
    avel
    0.09
    大çĪ±
    0.08
    anship
    0.08
    СТÐĴ
    0.07
    HasKey
    0.07
    ãĥĸãĥ«
    0.07
    urna
    0.07
    veli
    0.07
    envir
    0.07
    issage
    0.07
    Activations Density 0.001%

    No Known Activations