© 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. 1020
    Prev
    Next
    INDEX
    Explanations

    numbers and IDs

    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
     typingsJapgolly
    -0.24
    ãģªãģĦãģ§ãģĻ
    -0.21
    æ²Ļæ¼ł
    -0.20
    èĤĵ
    -0.20
    ìĬ¤íģ¬
    -0.20
    (nonatomic
    -0.20
    çŃļ
    -0.20
    itarian
    -0.19
    å¤įå·¥å¤į
    -0.19
    åŁ
    -0.18
    POSITIVE LOGITS
    @qq
    0.26
    <Renderer
    0.24
    zept
    0.22
    óst
    0.21
    <Props
    0.21
    NavController
    0.20
    uxt
    0.20
    onsense
    0.20
    cuador
    0.20
    .AutoScaleMode
    0.20
    Activations Density 0.461%

    No Known Activations