© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2935
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
    imbus
    -0.26
    ardown
    -0.26
    ¹Ħ
    -0.24
    rippling
    -0.23
    osate
    -0.23
    wcs
    -0.22
    줬
    -0.22
    饽
    -0.22
    :'.$
    -0.22
    UART
    -0.22
    POSITIVE LOGITS
    ä¸įæĸŃåıijå±ķ
    0.24
    ä¾ĽçĶµåħ¬åı¸
    0.20
     objectMapper
    0.20
    éĢĢåĽŀ
    0.19
    åĹIJ
    0.19
    æĿĤ
    0.18
    è½»æĺĵ
    0.18
     filmy
    0.18
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.17
     closets
    0.17
    Activations Density 0.001%

    No Known Activations