© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    need/require

    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
    ateur
    -0.23
    lassian
    -0.22
    detalle
    -0.22
    ocache
    -0.20
    (ConfigurationManager
    -0.20
    è½»æĺĵ
    -0.20
    .mybatis
    -0.20
    encion
    -0.19
    eworthy
    -0.19
     possible
    -0.19
    POSITIVE LOGITS
    èĩ¾
    0.34
    lessly
    0.27
    æīįèĥ½
    0.27
    é¢Ŀå¤ĸ
    0.25
    åħ·å¤ĩ
    0.22
    åĭĩæ°Ķ
    0.22
    çī¹åĪ«å£°æĺİ
    0.21
    /generated
    0.21
    çĮ
    0.21
    -know
    0.21
    Activations Density 1.877%

    No Known Activations