© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    system descriptions

    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
    ].'
    -0.32
     embod
    -0.29
    izador
    -0.27
    éŀŃ
    -0.23
     grated
    -0.23
    âĶĦ
    -0.23
     redhead
    -0.23
    -instagram
    -0.23
    GeV
    -0.23
    沪æĮĩ
    -0.22
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.42
    毫æĹłçĸij
    0.40
    çļĦ带é¢Ĩ
    0.36
    å¦Ĥæŀľçݩ家
    0.29
     Boehner
    0.29
    ä¾ĭå¦Ĥ
    0.28
    游æĪıè§Ĵèī²
    0.28
     jewish
    0.28
    Türkiye
    0.28
    çķĮ第ä¸Ģ
    0.27
    Activations Density 6.266%

    No Known Activations