© 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. 3597
    Prev
    Next
    INDEX
    Explanations

    code and meta information

    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
    .cgi
    -0.21
    åĽĽä¸ªèĩªä¿¡
    -0.20
     Kostenlos
    -0.19
    annabin
    -0.19
    ãģĻãģĶ
    -0.19
    IJèĹı
    -0.18
    createFrom
    -0.18
    asurer
    -0.18
    MDB
    -0.18
    OwnProperty
    -0.18
    POSITIVE LOGITS
    ä¸į平衡
    0.21
     },{
    0.20
    榫
    0.20
    Ķ
    0.19
     Bars
    0.19
    èĥĽ
    0.19
    ä¾ĺ
    0.19
    è¤Ĭ
    0.19
    bsolute
    0.18
    áµĴ
    0.18
    Activations Density 0.001%

    No Known Activations