© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    time and sequence

    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
    -scenes
    -0.23
    /Gate
    -0.23
    layan
    -0.22
    ynos
    -0.22
    :"-
    -0.21
     Escorts
    -0.21
    LETED
    -0.21
    åļħ
    -0.21
    åŃĢ
    -0.20
     ]}↵
    -0.20
    POSITIVE LOGITS
    .optString
    0.20
    nop
    0.19
    JKLM
    0.19
    æĦ«
    0.19
    讽
    0.18
     jsonArray
    0.18
    reve
    0.18
    SI
    0.18
    _inner
    0.18
     dequeue
    0.17
    Activations Density 0.001%

    No Known Activations