© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    .

    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
     poate
    -0.24
     âĺĨ
    -0.24
    @brief
    -0.23
     enthus
    -0.23
     hentai
    -0.23
     trebuie
    -0.23
     fkk
    -0.22
    ómo
    -0.22
    ~-~-
    -0.22
    itorio
    -0.22
    POSITIVE LOGITS
    <=$
    0.27
     when
    0.25
     if
    0.24
    å½ĵ
    0.21
     assume
    0.20
    when
    0.20
    JNIEnv
    0.20
    åģĩ设
    0.20
    strconv
    0.19
    =";↵
    0.19
    Activations Density 1.364%

    No Known Activations