© 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. 3825
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    :absolute
    -0.23
    ëŀ©
    -0.22
    idée
    -0.21
    onents
    -0.21
    morgan
    -0.20
    å·´èı²
    -0.20
     RouterModule
    -0.20
    ãĢĤwww
    -0.20
    Serviço
    -0.20
    eday
    -0.20
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.28
    ä¸ĢäºĽ
    0.25
    uxtap
    0.24
    åħ¶å®ĥ
    0.24
    rô
    0.23
    åĬłä¸Ĭ
    0.23
    佶
    0.23
    ulerAngles
    0.23
    ómo
    0.23
    -scalable
    0.22
    Activations Density 0.161%

    No Known Activations