© 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. 2475
    Prev
    Next
    INDEX
    Explanations

    absence of things

    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
    éĹ²
    -0.20
     PropertyInfo
    -0.20
    çĭ¬è§Ĵ
    -0.19
    .TabStop
    -0.19
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.19
    imb
    -0.18
    æµģåĬ¨æĢ§
    -0.18
    æ±¹
    -0.18
    lard
    -0.17
     Dem
    -0.17
    POSITIVE LOGITS
     traditional
    0.22
     Traditional
    0.22
    ãģĻãģĵãģ¨
    0.22
     )↵↵↵↵↵↵↵↵
    0.21
     spos
    0.21
     traditionally
    0.21
    ä¼łç»Ł
    0.21
    çīºçī²
    0.20
     requiring
    0.20
    éľĢ
    0.20
    Activations Density 0.457%

    No Known Activations