© 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. 1382
    Prev
    Next
    INDEX
    Explanations

    calculation

    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
    BootApplication
    -0.24
    .ERR
    -0.22
    /Dk
    -0.22
    \OptionsResolver
    -0.21
    .Measure
    -0.20
    YYY
    -0.20
    Todd
    -0.20
    vertisement
    -0.20
    ----------↵↵
    -0.19
    ,$_
    -0.19
    POSITIVE LOGITS
    estruction
    0.21
    ingles
    0.18
    ãģ½
    0.18
     onHide
    0.18
    ataka
    0.18
    .OneToOne
    0.18
    éĶ°
    0.18
    ãģįãĤĮ
    0.18
     UnityEditor
    0.17
     expectations
    0.17
    Activations Density 0.571%

    No Known Activations