© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 772
    Prev
    Next
    INDEX
    Explanations

    After

    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
    elmet
    -0.22
    utschen
    -0.20
     prosec
    -0.20
    ypad
    -0.19
    åĺŀ
    -0.19
    alach
    -0.19
     cellFor
    -0.19
     nomine
    -0.19
    unakan
    -0.18
    tractive
    -0.18
    POSITIVE LOGITS
    noon
    0.32
     initial
    0.30
    å®ĮæĪIJåIJİ
    0.27
     completion
    0.25
    effects
    0.25
    thought
    0.24
    سة
    0.24
    "After
    0.24
     Initial
    0.24
    ä¸Ģçķª
    0.23
    Activations Density 0.998%

    No Known Activations