© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    human activities and states

    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
    æĤ¨çļĦåŃ©åŃIJ
    -0.24
    .MouseAdapter
    -0.21
    iversary
    -0.20
    åľ¨è¿ĩ渡
    -0.20
    "errors
    -0.19
    "bytes
    -0.19
    ä¸Ģ个èģĮä¸ļ
    -0.19
    rikes
    -0.18
    abus
    -0.18
    rray
    -0.18
    POSITIVE LOGITS
     NEGLIGENCE
    0.23
     Premiership
    0.23
     ><?
    0.22
    ">ÃĹ</
    0.21
    ɨ
    0.21
     #=>
    0.21
    ().'/
    0.21
    ennifer
    0.21
    @stop
    0.20
    /stdc
    0.20
    Activations Density 0.117%

    No Known Activations