© 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. 717
    Prev
    Next
    INDEX
    Explanations

    code function

    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
    >čč↵
    -0.25
    çĽ´çº¿
    -0.20
     lorem
    -0.20
    expérience
    -0.20
    åĽĽæĸ¹
    -0.19
    /im
    -0.19
    psilon
    -0.19
    @Inject
    -0.19
    ound
    -0.19
    å·¥ä½ľç»ıéªĮ
    -0.18
    POSITIVE LOGITS
     EventArgs
    0.30
    [System
    0.25
     event
    0.24
     unused
    0.23
    unused
    0.23
     sender
    0.23
     Unused
    0.23
    avigator
    0.22
    )))));↵
    0.22
     e
    0.22
    Activations Density 0.736%

    No Known Activations