© 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. 1865
    Prev
    Next
    INDEX
    Explanations

    sent

    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
    èµ°ä¸ĭåİ»
    -0.23
    æģ£
    -0.22
    æĹ¶ä»£ä¸ŃåĽ½
    -0.22
     lokale
    -0.20
     kup
    -0.20
    .refs
    -0.20
    _KeyPress
    -0.20
    öffent
    -0.20
    aker
    -0.20
    _SelectedIndexChanged
    -0.19
    POSITIVE LOGITS
    asurer
    0.38
     onto
    0.36
     into
    0.33
    åĪ°
    0.33
    into
    0.29
    Into
    0.29
     Into
    0.29
    from
    0.28
    èĩ³
    0.28
     via
    0.27
    Activations Density 4.910%

    No Known Activations