© 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. 3631
    Prev
    Next
    INDEX
    Explanations

    promise

    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
     Verm
    -0.23
    åĸĦæĦı
    -0.22
     targetType
    -0.20
    outfile
    -0.20
     harmless
    -0.20
    ä¹Łåıªèĥ½
    -0.19
    è¾Ľ
    -0.18
    íķĺìĭ¤
    -0.18
     innoc
    -0.18
    åıįåĩ»
    -0.18
    POSITIVE LOGITS
    对å¾ħ
    0.23
    /List
    0.22
     promised
    0.22
    忽
    0.22
    æī¿è¯º
    0.21
    %;">
    0.21
    Thunk
    0.20
     promises
    0.20
    ä¸įå°½
    0.20
     promise
    0.20
    Activations Density 0.303%

    No Known Activations