© 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. 40757
    Prev
    Next
    INDEX
    Explanations

    math equations with variables

    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
    atik
    -0.07
    æķ£
    -0.07
     prov
    -0.07
    è¿ĻçĤ¹
    -0.07
    acie
    -0.07
    kev
    -0.07
    apas
    -0.06
    asuk
    -0.06
    rame
    -0.06
    ozo
    -0.06
    POSITIVE LOGITS
    adores
    0.07
    adura
    0.07
    éĶµ
    0.07
    zinha
    0.07
    ķĮ
    0.07
    обÑĢа
    0.07
    adora
    0.07
    tora
    0.07
    unga
    0.07
    åѦèĢĮ
    0.07
    Activations Density 0.006%

    No Known Activations