© 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. 57772
    Prev
    Next
    INDEX
    Explanations

    telephone modular housing

    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
    æľ¬ç«ĻåĨħ容
    -0.08
    roys
    -0.07
    åĿIJåĪ°
    -0.07
    oroz
    -0.07
    å²Ń
    -0.07
    yz
    -0.07
    insa
    -0.07
    irman
    -0.06
     <![
    -0.06
     PRESID
    -0.06
    POSITIVE LOGITS
     famously
    0.07
    æľĢèijĹåIJįçļĦ
    0.06
    grave
    0.06
    ÙĪÙĬÙĨ
    0.06
    åįĥåı¤
    0.06
    agro
    0.06
    nese
    0.06
    ä¸İå®ŀéĻħ
    0.06
    ase
    0.06
    _TW
    0.06
    Activations Density 0.226%

    No Known Activations