© 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. 1647
    Prev
    Next
    INDEX
    Explanations

    technical jargon

    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
    毫æĹłçĸij
    -0.37
     èĩªåĬ¨çĶŁæĪIJ
    -0.37
    (___
    -0.35
    æį¢åı¥è¯Ŀ
    -0.35
    благо
    -0.34
    herits
    -0.33
    âĨ©
    -0.33
    ãİŀ
    -0.32
    åĨ°æ·ĩ
    -0.31
    -Compatible
    -0.31
    POSITIVE LOGITS
     jMenuItem
    0.27
    -
    0.25
    -toggler
    0.24
    ephy
    0.24
     '-')
    0.24
     empres
    0.23
    ï¼Ī
    0.23
    abbix
    0.22
    PDOException
    0.21
     emploi
    0.21
    Activations Density 8.316%

    No Known Activations