© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4050
    Prev
    Next
    INDEX
    Explanations

    legal writing

    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
    ðŁĶİ
    -0.22
    .fm
    -0.21
    Wunused
    -0.20
    èŀ³
    -0.20
    ://%
    -0.19
    ç¾°
    -0.19
    asmus
    -0.19
    .ie
    -0.19
    ENTIC
    -0.19
    ppard
    -0.19
    POSITIVE LOGITS
    åĪ¹è½¦
    0.20
    thic
    0.20
    .getElementsByName
    0.19
     dated
    0.19
    mmas
    0.19
    ivid
    0.18
    .ByteString
    0.18
    /input
    0.18
    emplates
    0.18
    å¼ĢèĬ±
    0.18
    Activations Density 0.856%

    No Known Activations