© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3802
    Prev
    Next
    INDEX
    Explanations

    cities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    addir
    -0.22
    lashes
    -0.21
    ocrats
    -0.21
    ;?>↵
    -0.21
    .statusText
    -0.20
    ESSAGES
    -0.20
    [--
    -0.20
    宾
    -0.20
     }?>↵
    -0.20
    },č↵č↵
    -0.20
    POSITIVE LOGITS
     city
    0.24
    EventListener
    0.22
     skyline
    0.22
    éĥ½å¸Ĥ
    0.21
    .Strict
    0.21
    city
    0.20
     metropolitan
    0.20
    buat
    0.19
     City
    0.19
    _city
    0.19
    Activations Density 0.382%

    No Known Activations