© 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. 2640
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    criptors
    -0.26
    被èªī
    -0.22
    代
    -0.20
    åĬŁè¯¾
    -0.20
    âīĥ
    -0.20
    èģĴ
    -0.19
    agara
    -0.19
     tys
    -0.19
    ForRow
    -0.18
    -Bold
    -0.18
    POSITIVE LOGITS
    anmar
    0.23
    obook
    0.22
    ymoon
    0.20
    ymm
    0.20
    ategorized
    0.20
    ÇĶ
    0.19
    drs
    0.19
    itarian
    0.19
    ",__
    0.18
    :result
    0.18
    Activations Density 0.002%

    No Known Activations