© 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. 2686
    Prev
    Next
    INDEX
    Explanations

    antibodies

    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
    agen
    -0.20
    angkan
    -0.20
    ä¸įèī¯ä¿¡æģ¯
    -0.20
    註
    -0.20
    éĻĨ
    -0.19
    íķĺìĭ¤
    -0.19
     grandi
    -0.19
    ItemCount
    -0.18
    诺
    -0.18
     Registrar
    -0.18
    POSITIVE LOGITS
    conexao
    0.30
    æ±
    0.25
    æĬĹä½ĵ
    0.23
    incy
    0.23
    ä¸ŃåĽ½ç½ij游
    0.23
    å°±ç»Ļ大家
    0.22
    游æĪıåī¯æľ¬
    0.21
     antibodies
    0.21
    \Bridge
    0.21
    ,");↵
    0.21
    Activations Density 0.056%

    No Known Activations