© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    structured data

    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
    cai
    -0.22
    .AI
    -0.21
    byss
    -0.21
    æĭĹ
    -0.20
    Aceptar
    -0.20
    游æĪıéĩĮçļĦ
    -0.19
    çªĹæĪ·
    -0.19
    æ½ľ
    -0.19
    æı£
    -0.19
    .Pin
    -0.18
    POSITIVE LOGITS
    IFn
    0.30
    engeance
    0.24
    _tD
    0.23
    elmet
    0.22
    _tA
    0.21
    å½¹
    0.20
    scious
    0.20
    zik
    0.20
    -Trump
    0.20
    éĩįè¦ģåİŁåĽł
    0.20
    Activations Density 0.001%

    No Known Activations