© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    common or typical

    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
    (strpos
    -0.22
    åįķ纯çļĦ
    -0.19
     !");↵
    -0.19
    Votre
    -0.19
    åįķ纯
    -0.19
    DetailsService
    -0.18
    EXP
    -0.18
    wards
    -0.18
    rå
    -0.18
    ."),
    -0.17
    POSITIVE LOGITS
     typical
    0.46
    常è§ģ
    0.43
    常è§ģçļĦ
    0.42
     commonly
    0.40
     realistic
    0.40
    åħ¸åŀĭ
    0.38
     common
    0.37
    常çĶ¨
    0.37
     Typical
    0.36
    typ
    0.35
    Activations Density 0.928%

    No Known Activations