© 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. 2883
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
     xamarin
    -0.27
    isan
    -0.20
    MMdd
    -0.20
    åijĺ
    -0.20
    ds
    -0.20
    é¾ĩ
    -0.20
    å¾ģ
    -0.20
     anál
    -0.20
     nomine
    -0.19
    fr
    -0.19
    POSITIVE LOGITS
    polator
    0.26
    ]int
    0.24
    phinx
    0.24
    _crit
    0.22
    luetooth
    0.22
    ì¦IJ
    0.22
    .GetEnumerator
    0.20
     inkl
    0.20
    Slinky
    0.20
    uplicates
    0.20
    Activations Density 0.016%

    No Known Activations