© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1555
    Prev
    Next
    INDEX
    Explanations

    'O' or 'S' names

    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
     Politico
    -0.20
    éĹ³
    -0.20
    Č
    -0.20
    atori
    -0.19
    /XMLSchema
    -0.19
    ูà¸ģ
    -0.18
    éºĩ
    -0.18
    ottenham
    -0.18
    ammen
    -0.18
    èµį
    -0.18
    POSITIVE LOGITS
    uncture
    0.20
    æİĤ
    0.20
    ($(".
    0.20
     básico
    0.20
     :↵↵↵↵
    0.19
     defStyleAttr
    0.18
    èī³
    0.18
    'icon
    0.18
    iates
    0.18
    pac
    0.18
    Activations Density 0.005%

    No Known Activations