© 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. 2420
    Prev
    Next
    INDEX
    Explanations

    human

    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
     Canadiens
    -0.21
    bian
    -0.21
    _sta
    -0.20
     ypos
    -0.20
    edly
    -0.20
     toReturn
    -0.20
    tridges
    -0.19
     advoc
    -0.19
     strstr
    -0.19
    (EFFECT
    -0.19
    POSITIVE LOGITS
    -human
    0.27
    DMETHOD
    0.27
     human
    0.27
     beings
    0.27
     meiden
    0.24
    human
    0.24
     ><?
    0.24
     замеÑĩа
    0.23
     Human
    0.23
     humans
    0.23
    Activations Density 0.097%

    No Known Activations