© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    specific labels

    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
     PartialView
    -0.20
    indow
    -0.20
     =>$
    -0.20
    æĮŀ
    -0.19
    oise
    -0.19
    exterity
    -0.19
    airo
    -0.19
    踵
    -0.19
    ç©¿éĢı
    -0.18
    obuf
    -0.18
    POSITIVE LOGITS
     beneficiation
    0.21
    linkplain
    0.20
    åijĹ
    0.20
    ire
    0.20
    âľĺ
    0.19
    éĢīæĭ
    0.19
     CircularProgress
    0.19
    ForMember
    0.19
    stral
    0.18
     frankfurt
    0.18
    Activations Density 0.001%

    No Known Activations