© 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. 1352
    Prev
    Next
    INDEX
    Explanations

    technical or foreign

    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
    afür
    -0.23
    emain
    -0.21
    agascar
    -0.20
    bane
    -0.20
    awning
    -0.19
    @Test
    -0.19
    adro
    -0.19
    å¼¥
    -0.19
     íĨµíķ´ìĦľ
    -0.18
    izzling
    -0.18
    POSITIVE LOGITS
     bénéficie
    0.26
    etal
    0.21
    æĺ±
    0.21
    ãİŀ
    0.21
    Investigators
    0.20
    èĥ³
    0.20
    xdf
    0.19
    å¾ģæĶ¶
    0.19
     CORPOR
    0.19
    OLA
    0.19
    Activations Density 0.002%

    No Known Activations