© 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. 1633
    Prev
    Next
    INDEX
    Explanations

    specific acronyms or terms

    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
    =-=-=-=-
    -0.28
    =-=-
    -0.28
    aeda
    -0.26
    èĻĵ
    -0.26
    ç¡ķ士çłĶ究
    -0.26
    çݩ家æľĭåıĭ
    -0.25
    .dtd
    -0.25
    <path
    -0.24
    .parseLong
    -0.24
    ancode
    -0.24
    POSITIVE LOGITS
    æĢ§ä»·
    0.30
    åıĸåĨ³
    0.25
    磧
    0.24
     consc
    0.23
     semiclass
    0.23
    æīĢæīĢéķ¿
    0.21
    娱ä¹IJå¹³åı°
    0.21
    女æĢ§æľĭåıĭ
    0.21
    ç½ijé¦ĸ页
    0.21
    åĶ·
    0.20
    Activations Density 17.691%

    No Known Activations