© 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. 3607
    Prev
    Next
    INDEX
    Explanations

    specific names and contexts

    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
     ActionTypes
    -0.26
     e
    -0.21
    aland
    -0.20
     EPA
    -0.20
    åĶı
    -0.19
    åįĥéĩĮ
    -0.19
    ally
    -0.19
    .ready
    -0.18
    榨
    -0.18
    aus
    -0.18
    POSITIVE LOGITS
    -Cs
    0.27
    ".↵↵↵↵
    0.27
    ?"↵↵↵↵
    0.22
    upported
    0.22
    .Never
    0.21
    renom
    0.21
    /Private
    0.20
     libertine
    0.20
    isbury
    0.20
    >Password
    0.20
    Activations Density 0.001%

    No Known Activations