© 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. 51390
    Prev
    Next
    INDEX
    Explanations

    office/death/sales ratios

    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
    ignon
    -0.07
    åĽ´
    -0.07
    æľīç¼ĺ
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.06
    mailer
    -0.06
     Fortune
    -0.06
    ä¹ł
    -0.06
     oán
    -0.06
    ä¿ĥè¿Ľä¼ļ
    -0.06
    akedown
    -0.06
    POSITIVE LOGITS
     fucked
    0.08
    ostro
    0.07
    LEC
    0.07
     gente
    0.07
    ramer
    0.07
    otra
    0.07
    awas
    0.07
    unic
    0.07
    çļĦè¿Ļ个
    0.07
    _refs
    0.07
    Activations Density 0.002%

    No Known Activations