© 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. 3011
    Prev
    Next
    INDEX
    Explanations

    lawyer, attorney, counsel

    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
    valueOf
    -0.22
     ComponentFixture
    -0.21
    lijah
    -0.20
    >Returns
    -0.20
    elaide
    -0.19
    ãģĵãģ¨ãĤĤãģĤãĤĬãģ¾ãģĻ
    -0.19
    ocking
    -0.19
    åıī
    -0.19
    å¡«è¡¥
    -0.18
    ynthia
    -0.18
    POSITIVE LOGITS
    æī§ä¸ļ
    0.36
     client
    0.35
     clients
    0.34
    client
    0.33
    -client
    0.33
    clients
    0.32
    客æĪ·ç«¯
    0.31
     Clients
    0.30
    _clients
    0.30
    lient
    0.29
    Activations Density 0.400%

    No Known Activations