© 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. 3359
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èĤ¤èī²
    -0.21
     nghìn
    -0.20
     misd
    -0.19
    ãĥµ
    -0.19
    åĬŁ
    -0.18
    -prepend
    -0.18
     cameo
    -0.18
    å¾ĭ
    -0.18
    -unstyled
    -0.18
    aml
    -0.18
    POSITIVE LOGITS
    ðŁĵIJ
    0.33
    rvine
    0.28
    âļĹ
    0.28
    )./
    0.23
    >manual
    0.22
    stanbul
    0.21
     bindActionCreators
    0.21
    alité
    0.21
     lucr
    0.21
    对åħ¶çľŁå®ŀ
    0.21
    Activations Density 0.000%

    No Known Activations