© 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. 2724
    Prev
    Next
    INDEX
    Explanations

    places

    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
     ++)↵
    -0.23
    onestly
    -0.22
     headquartered
    -0.22
    ickey
    -0.20
    ooter
    -0.20
    è±ģ
    -0.20
    Cerrar
    -0.19
    .BLL
    -0.19
     Prev
    -0.19
     DataTypes
    -0.19
    POSITIVE LOGITS
    iosk
    0.23
    åľŁèĢ³
    0.23
    ожеÑĤ
    0.22
    äºĵ
    0.22
    notated
    0.21
    iguiente
    0.21
    导è´Ń
    0.20
    éĩįè¦ģåİŁåĽł
    0.20
    代
    0.20
    bic
    0.20
    Activations Density 0.493%

    No Known Activations