© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    çĮĸ
    -0.24
    å¬Ĺ
    -0.21
    ...
    -0.21
    åĴİ
    -0.21
     fi
    -0.21
    fabs
    -0.20
    _most
    -0.20
    解æĶ¾æĢĿæĥ³
    -0.20
     contr
    -0.20
    æĪ¿è½¦
    -0.20
    POSITIVE LOGITS
     Jackets
    0.24
    cakes
    0.24
     nrw
    0.23
     GOODS
    0.23
     excer
    0.23
     PROVIDED
    0.23
     идеалÑĮн
    0.23
    /Instruction
    0.22
    icap
    0.22
     strugg
    0.22
    Activations Density 3.615%

    No Known Activations