© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    abbreviations and technical terms

    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
    ]={↵
    -0.26
    .vs
    -0.23
    /accounts
    -0.22
    çĶŁäºİ
    -0.21
    )((((
    -0.21
    abhängig
    -0.21
    );;↵
    -0.21
     bindActionCreators
    -0.20
     Gä
    -0.20
    /styles
    -0.20
    POSITIVE LOGITS
    è°«
    0.21
    --[[
    0.21
     boobs
    0.20
    orgeous
    0.19
    èħŃ
    0.19
    èijŃ
    0.19
    HBoxLayout
    0.19
    åħĥå·¦åı³
    0.19
     pictureBox
    0.18
    黯
    0.18
    Activations Density 0.010%

    No Known Activations