© 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. 653
    Prev
    Next
    INDEX
    Explanations

    descriptive text snippets

    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
    æĢ§ä»·
    -0.25
     *</
    -0.21
    ç½ijé¦ĸ页
    -0.21
     verschiedene
    -0.20
     tô
    -0.20
    põe
    -0.19
     pérdida
    -0.18
    åĤ³éĢģ
    -0.18
    #ac
    -0.18
    å¤įå·¥å¤į
    -0.18
    POSITIVE LOGITS
     pione
    0.18
     Noticed
    0.17
     strugg
    0.17
     ApplicationException
    0.17
    retorno
    0.15
    caracter
    0.15
     Também
    0.15
     desar
    0.15
     RaycastHit
    0.15
    RequestParam
    0.15
    Activations Density 0.963%

    No Known Activations