© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 536
    Prev
    Next
    INDEX
    Explanations

    web links

    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
    娱ä¹IJå¹³åı°
    -0.34
    .BorderFactory
    -0.25
    åĢĴåľ¨åľ°
    -0.25
    女æĢ§æľĭåıĭ
    -0.24
    个交æĺĵ
    -0.23
     prive
    -0.23
    çݩ家æľĭåıĭ
    -0.22
    usterity
    -0.22
    .SwingConstants
    -0.21
    åĺļ
    -0.21
    POSITIVE LOGITS
     http
    0.42
     https
    0.38
    http
    0.35
    :http
    0.33
     link
    0.33
    https
    0.32
    -http
    0.30
     HERE
    0.30
    éĵ¾æİ¥
    0.30
    (http
    0.29
    Activations Density 4.310%

    No Known Activations