© 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. 2583
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    éĤ£ä¹Ī容æĺĵ
    -0.20
    ÑĥниÑĨип
    -0.20
    积
    -0.19
    atz
    -0.19
    ä¸ŃéĢĶ
    -0.19
    éªĢ
    -0.19
    puty
    -0.18
     doInBackground
    -0.18
    个çĻ¾åĪĨ
    -0.18
    ê²¹
    -0.18
    POSITIVE LOGITS
    adastro
    0.24
    oggler
    0.20
    æıIJæĭĶ
    0.20
    éĴ½
    0.20
     Logged
    0.19
     tÃŃ
    0.19
     Positioned
    0.19
    OUR
    0.19
    ogle
    0.19
    REAM
    0.19
    Activations Density 0.002%

    No Known Activations