© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    changing state or value

    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
    :';↵
    -0.25
    weeted
    -0.24
    istributor
    -0.24
    oundation
    -0.22
    icode
    -0.22
    almart
    -0.22
    intage
    -0.21
    æĸ°æµªå¾®åįļ
    -0.21
    .ToShort
    -0.21
    :'.$
    -0.21
    POSITIVE LOGITS
     plateau
    0.24
    稳å®ļ
    0.23
    ç»´æĮģ
    0.22
    è¾¾åĪ°
    0.22
    reach
    0.22
    è¾¾
    0.21
     Maint
    0.20
     leveling
    0.20
    plate
    0.20
    ç¶Ń
    0.19
    Activations Density 0.274%

    No Known Activations