© 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. 34
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
    -strokes
    -0.43
    anmar
    -0.40
     èĩªåĬ¨çĶŁæĪIJ
    -0.40
     )↵↵↵↵↵↵↵↵
    -0.39
     molec
    -0.37
     recru
    -0.36
     MILF
    -0.36
    volución
    -0.35
     tremend
    -0.35
    irlines
    -0.34
    POSITIVE LOGITS
     and
    0.27
    Feels
    0.27
     the
    0.26
     an
    0.26
     non
    0.26
    åºĭ
    0.26
    æĭľå¸Ī
    0.25
     information
    0.25
     data
    0.24
    亲çĪ±
    0.24
    Activations Density 6.936%

    No Known Activations