© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 671
    Prev
    Next
    INDEX
    Explanations

    read later content

    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
    !=(
    -0.29
     ******************************************************************************↵
    -0.28
    åıĭæĥħéĵ¾æİ¥
    -0.28
    <=(
    -0.28
    éĥ¨åī¯
    -0.24
    讧
    -0.24
    ãĥĵãĤ¸ãĥį
    -0.24
    peater
    -0.23
    -eslint
    -0.23
    (Have
    -0.22
    POSITIVE LOGITS
    æ©ĩ
    0.22
     imgUrl
    0.22
    -uppercase
    0.22
     ReturnType
    0.21
    ultimo
    0.21
    çĻĶ
    0.21
    åł°
    0.20
    åĥĸ
    0.20
     companyName
    0.20
     orth
    0.20
    Activations Density 3.247%

    No Known Activations