© 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. 33955
    Prev
    Next
    INDEX
    Explanations

    pipeline and workflows

    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
    ials
    -0.08
    iglio
    -0.07
    itivity
    -0.07
    ivate
    -0.07
    ivel
    -0.07
    ucker
    -0.07
    /comment
    -0.07
    anyi
    -0.07
    ç½ijåıĭè¯Ħ论
    -0.07
    SION
    -0.07
    POSITIVE LOGITS
    åľ¨çĽ®
    0.09
    =https
    0.08
    çĭĪ
    0.08
    ÙĩØ©
    0.08
    ÑĥÑĤÑĮ
    0.08
    ãģ«æ²¿
    0.07
     заÑģед
    0.07
    åĨįéĢł
    0.07
    icke
    0.07
    mÃ¤ÃŁig
    0.07
    Activations Density 0.037%

    No Known Activations