© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17933
    Prev
    Next
    INDEX
    Explanations

    city or town names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gesta
    -0.06
    ive
    -0.06
    ante
    -0.06
    NIK
    -0.06
    ÙĬØ©
    -0.06
    uper
    -0.06
     Passe
    -0.06
    ért
    -0.06
     agit
    -0.06
    ud
    -0.06
    POSITIVE LOGITS
     subs
    0.05
     âĤ
    0.05
     aux
    0.05
    åİ¿åŁİ
    0.05
    /platform
    0.05
    nes
    0.05
    ulangan
    0.05
    plication
    0.05
    neau
    0.05
     adj
    0.05
    Activations Density 0.040%

    No Known Activations