© 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. 2620
    Prev
    Next
    INDEX
    Explanations

    |

    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
    æĥ®
    -0.19
    -animate
    -0.19
    aghetti
    -0.19
     culo
    -0.18
    .OrderByDescending
    -0.18
     -
    -0.18
    è¯Ĩ
    -0.18
     wakeup
    -0.18
     migliori
    -0.18
     (
    -0.18
    POSITIVE LOGITS
    Serviço
    0.28
    .newArrayList
    0.24
    ?option
    0.22
    ËĬ
    0.22
    .RELATED
    0.22
    æĿ¨æ¬¢
    0.20
     ['.
    0.20
    .easy
    0.20
    .heroku
    0.20
    æ°ķ
    0.20
    Activations Density 0.027%

    No Known Activations