© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    Code and technical terms

    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
     esk
    -0.25
    bindValue
    -0.23
    黢
    -0.22
    cased
    -0.21
    dojo
    -0.20
     iht
    -0.20
    ennie
    -0.20
    Islamic
    -0.19
    }());↵
    -0.19
    çĸ²åĬ³
    -0.19
    POSITIVE LOGITS
     hely
    0.20
     Und
    0.20
     Premiership
    0.19
    缣
    0.19
    loomberg
    0.18
    Mo
    0.18
    ');↵↵↵↵
    0.18
    QueryParam
    0.18
    lain
    0.18
    ãi
    0.18
    Activations Density 0.001%

    No Known Activations