© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    the

    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
    并ä¸įæĺ¯å¾Ī
    -0.27
    æijĩäºĨ
    -0.26
    ampie
    -0.26
    åŁºæľ¬ä¸Ĭéĥ½
    -0.24
     walmart
    -0.24
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    -0.23
     methodName
    -0.23
    .'/'.$
    -0.23
     Fortnite
    -0.22
    诨
    -0.22
    POSITIVE LOGITS
    imagenes
    0.28
     CommandType
    0.24
    taÅŁ
    0.23
    ábado
    0.22
     Erotic
    0.21
    beginTransaction
    0.21
    reducers
    0.20
    éparation
    0.20
    evity
    0.20
     sublic
    0.20
    Activations Density 4.629%

    No Known Activations