© 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. 2298
    Prev
    Next
    INDEX
    Explanations

    shared or communicated

    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
    opération
    -0.22
    ;}↵↵
    -0.22
    ibraltar
    -0.21
    ++){↵↵
    -0.21
    orgeous
    -0.21
    eneg
    -0.20
     è¾ĵ
    -0.20
     avalia
    -0.20
    avana
    -0.20
    é«
    -0.20
    POSITIVE LOGITS
    ESSAGES
    0.26
    åĽ½éĻħåľ¨çº¿
    0.22
    <Renderer
    0.21
    interop
    0.21
    czÄĻ
    0.20
    {-#
    0.20
     meld
    0.20
    twor
    0.20
    ))==
    0.20
    .bits
    0.20
    Activations Density 0.823%

    No Known Activations