© 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. 2249
    Prev
    Next
    INDEX
    Explanations

    German technical text

    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
     lick
    -0.21
    æıĨ
    -0.19
    管çIJĨä¸Ńå¿ĥ
    -0.19
    routeProvider
    -0.19
    apol
    -0.18
     [~,
    -0.18
    naments
    -0.18
    ToObject
    -0.18
    æ·±
    -0.18
    ãģĤãĤĬãģ¾ãģĽãĤĵ
    -0.18
    POSITIVE LOGITS
    )))),
    0.28
    rvine
    0.26
    .§
    0.24
    :numel
    0.24
     Ãĸn
    0.23
    /MPL
    0.22
    )))));↵
    0.22
    .ObjectMeta
    0.21
    :".$
    0.21
    ONO
    0.21
    Activations Density 0.007%

    No Known Activations