© 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. 2635
    Prev
    Next
    INDEX
    Explanations

    mixed content

    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
    èĥĦ
    -0.19
     endereco
    -0.18
    _initialized
    -0.18
    undry
    -0.17
    to
    -0.17
    azen
    -0.17
     Pin
    -0.17
     feelings
    -0.17
     scaffold
    -0.17
     hints
    -0.17
    POSITIVE LOGITS
    ëŀĦ
    0.25
    )((((
    0.24
    /effects
    0.23
    برÙĬطاÙĨÙĬا
    0.23
    âīĥ
    0.23
    uxtap
    0.22
    #ab
    0.22
     Prostit
    0.21
    âĬ
    0.21
    âĩIJ
    0.21
    Activations Density 0.001%

    No Known Activations