© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    movie titles

    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
     Dzi
    -0.23
    ].'
    -0.22
    qus
    -0.21
    âĺ°
    -0.21
     makeStyles
    -0.21
     spécialisé
    -0.21
    quartered
    -0.20
    yntax
    -0.20
    ebin
    -0.20
    =<?=$
    -0.20
    POSITIVE LOGITS
    chts
    0.23
    (DialogInterface
    0.22
    /bower
    0.21
    ¸
    0.21
    ç»ĵæĿŁåIJİ
    0.19
    å§Ĭ妹
    0.19
    çĸ¡
    0.19
    éĹ´æİ¥
    0.18
    ités
    0.18
    åĩºå·®
    0.18
    Activations Density 0.529%

    No Known Activations