© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    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
    extrême
    -0.20
     potrÃł
    -0.20
    ANCES
    -0.20
    );}
    -0.19
    enville
    -0.19
     jim
    -0.19
     roma
    -0.19
    ĵį
    -0.19
    ElementException
    -0.18
    raries
    -0.18
    POSITIVE LOGITS
     beÄŁen
    0.23
    /Dk
    0.22
    @store
    0.20
    å¾ij
    0.20
    âĬ¿
    0.19
    .Properties
    0.19
    @show
    0.19
    à¤Ĩ
    0.19
    @Id
    0.18
    ligne
    0.18
    Activations Density 0.001%

    No Known Activations