© 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. 605
    Prev
    Next
    INDEX
    Explanations

    There is

    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
    CCCCCC
    -0.24
    /filepath
    -0.24
    logue
    -0.23
    =?,
    -0.22
    HELL
    -0.22
    ç§ijæĬĢèĤ¡ä»½
    -0.22
    ucson
    -0.21
    .rar
    -0.20
    èĭ«
    -0.20
    rary
    -0.20
    POSITIVE LOGITS
    ábado
    0.27
     no
    0.26
     plenty
    0.25
     room
    0.24
    ,no
    0.23
     reason
    0.23
    -no
    0.22
    åı¯ä¾Ľ
    0.22
     danger
    0.22
    overlap
    0.22
    Activations Density 1.036%

    No Known Activations