© 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. 957
    Prev
    Next
    INDEX
    Explanations

    Personal or publication details

    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
    ----</
    -0.28
    __;↵
    -0.28
    ","");↵
    -0.26
    -Methods
    -0.26
    PURE
    -0.25
    âĸ¹
    -0.25
    Ī
    -0.25
     ){↵↵
    -0.24
    ','');↵
    -0.24
     Khá
    -0.24
    POSITIVE LOGITS
     bigot
    0.26
    ↵↵
    0.23
     voyeur
    0.22
     consulate
    0.22
    \n
    0.21
    身亡
    0.21
    ToLeft
    0.20
     airstrikes
    0.20
    Wunused
    0.20
    аÐ
    0.20
    Activations Density 1.896%

    No Known Activations