© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2788
    Prev
    Next
    INDEX
    Explanations

    standpoint perspective

    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
    .RunWith
    -0.24
    ä»İä¸Ń
    -0.22
    ä»İ
    -0.22
    afür
    -0.21
    _vlog
    -0.21
    .shuffle
    -0.21
    ebile
    -0.20
     từ
    -0.20
    .fromFunction
    -0.20
     )↵↵↵↵↵↵↵↵
    -0.20
    POSITIVE LOGITS
     standpoint
    0.46
    çļĦè§Ĵ度
    0.38
     perspective
    0.37
    åģļèµ·
    0.35
     outset
    0.33
     sources
    0.32
    åĩºåıij
    0.30
    åħ¥æīĭ
    0.28
    sources
    0.28
     perspectives
    0.27
    Activations Density 0.984%

    No Known Activations