© 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. 2348
    Prev
    Next
    INDEX
    Explanations

    say "."

    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
    åľ¨ä¼łå¥ĩ
    -0.25
    ,www
    -0.21
    IDEOS
    -0.21
    âĢ¼
    -0.21
    positor
    -0.21
    )))));↵
    -0.21
    âĻĢ
    -0.20
    ija
    -0.20
    âĻ«
    -0.19
    /--
    -0.19
    POSITIVE LOGITS
    .
    0.23
    ?=.*
    0.23
     dut
    0.21
    /Dk
    0.20
    veis
    0.19
    Äĥr
    0.19
    reno
    0.19
    almart
    0.18
    strpos
    0.18
    opleft
    0.18
    Activations Density 0.133%

    No Known Activations