© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 929
    Prev
    Next
    INDEX
    Explanations

    technical code

    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
    -0.30
    icester
    -0.28
    acı
    -0.26
    ,
    -0.25
    achinery
    -0.23
    1
    -0.23
    ogie
    -0.23
    estatus
    -0.23
    ;o
    -0.23
    зван
    -0.23
    POSITIVE LOGITS
    娱ä¹IJå¹³åı°
    0.42
    åı¯ä»¥æĽ´å¥½
    0.36
    éļıæŶéļı
    0.35
    ä»İæł¹æľ¬
    0.35
    å¤įå·¥å¤į
    0.32
    éĢīæĭ
    0.32
    åħļé£İ
    0.31
    åĭł
    0.30
    ä¸Ģèĩ´å¥½è¯Ħ
    0.30
    ç½ijæĬķ
    0.30
    Activations Density 7.375%

    No Known Activations