© 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. 1799
    Prev
    Next
    INDEX
    Explanations

    specific word parts

    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
    enegro
    -0.20
     siden
    -0.20
    è¶ĭ
    -0.20
    vably
    -0.20
    JECTED
    -0.20
     gode
    -0.19
    .ElementAt
    -0.19
     australia
    -0.19
    ä¿Ħ
    -0.18
    èµħ
    -0.18
    POSITIVE LOGITS
    ")));
    0.25
    -www
    0.24
    ALLERY
    0.24
     Erectile
    0.23
    vsp
    0.22
     FindObjectOfType
    0.22
    caffold
    0.22
    deo
    0.22
    *sp
    0.22
    lke
    0.22
    Activations Density 0.009%

    No Known Activations