© 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. 1085
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    /socket
    -0.23
    :@""
    -0.20
    èĽ¾
    -0.20
    Erot
    -0.19
    eway
    -0.19
    ouston
    -0.19
    quet
    -0.18
    å°Ĩé¢Ĩ
    -0.18
    ROLL
    -0.18
    íĶĦë¡ľê·¸ëŀ¨
    -0.18
    POSITIVE LOGITS
    á¾±
    0.20
    rush
    0.20
    ambi
    0.19
     pers
    0.19
    ḳ
    0.19
    opsy
    0.19
    .ObjectMeta
    0.19
    ophon
    0.18
    .Office
    0.18
    Extern
    0.18
    Activations Density 0.000%

    No Known Activations