© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1105
    Prev
    Next
    INDEX
    Explanations

    Header or starting text

    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
    yor
    -0.25
     ($("#
    -0.20
    家éĥ½çŁ¥éģĵ
    -0.20
     strtoupper
    -0.20
    IEnumerator
    -0.19
     yans
    -0.19
    åºĶæĶ¶è´¦
    -0.19
    PrototypeOf
    -0.19
     ($('#
    -0.19
    "default
    -0.18
    POSITIVE LOGITS
    icaid
    0.22
    ë³į
    0.22
    æ¤ħ
    0.21
    pering
    0.21
    psc
    0.20
    elsinki
    0.20
     fri
    0.20
    undai
    0.20
    /Set
    0.19
    .ActionListener
    0.19
    Activations Density 0.001%

    No Known Activations