© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 56
    Prev
    Next
    INDEX
    Explanations

    there

    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
    rende
    -0.25
    phalt
    -0.23
     onResponse
    -0.21
     mouseClicked
    -0.20
     onFailure
    -0.20
     gode
    -0.20
    getSingleton
    -0.20
    eln
    -0.20
    utzer
    -0.19
    yon
    -0.19
    POSITIVE LOGITS
    /Dk
    0.37
    usterity
    0.28
    fühl
    0.24
    abouts
    0.24
    entifier
    0.24
    благо
    0.23
     Erectile
    0.23
    IFn
    0.22
     UnityEditor
    0.21
    建档ç«ĭ
    0.21
    Activations Density 0.309%

    No Known Activations