© 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. 861
    Prev
    Next
    INDEX
    Explanations

    special characters

    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
    [
    -0.24
    0
    -0.24
    1
    -0.23
    -
    -0.23
    èµ°åĬ¿åĽ¾
    -0.22
    (
    -0.21
    '
    -0.21
    éĺµåľ°
    -0.21
    {
    -0.21
    "
    -0.20
    POSITIVE LOGITS
    /MPL
    0.42
    /Instruction
    0.37
    /↵↵↵↵
    0.33
     çĶŁåij½åij¨æľŁ
    0.33
    Intialized
    0.31
    -League
    0.31
    -With
    0.31
    说å®ŀ
    0.31
    ,www
    0.30
    #ga
    0.30
    Activations Density 3.841%

    No Known Activations