© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    formatting

    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
    man
    -0.34
    -0.24
    jen
    -0.23
    arrants
    -0.23
    en
    -0.22
    ant
    -0.22
    an
    -0.22
    ian
    -0.22
    аниÑİ
    -0.22
    -0.21
    POSITIVE LOGITS
    istic
    0.28
    ists
    0.25
    0.24
    主ä¹īèĢħ
    0.23
    0.23
     ----------------
    0.22
    0.22
    0.22
    主ä¹ī
    0.22
    0.22
    Activations Density 0.254%

    No Known Activations