© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    central nervous system

    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
    linky
    -0.30
    oriously
    -0.26
     Playoff
    -0.25
    umpt
    -0.24
    Ẩ
    -0.24
    esteem
    -0.23
    orious
    -0.23
     fick
    -0.23
    itori
    -0.23
     Prostit
    -0.23
    POSITIVE LOGITS
    миниÑģÑĤ
    0.27
    emia
    0.22
    аÑĤегоÑĢ
    0.22
    ity
    0.22
    s
    0.21
    åľŁèĢ³
    0.20
     ÙĪسÙĦÙħ
    0.20
    æģ¯æģ¯
    0.20
    æģļ
    0.20
     rval
    0.19
    Activations Density 4.714%

    No Known Activations