© 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. 142
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations or codes

    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
    pell
    -0.23
     èĩªåĬ¨çĶŁæĪIJ
    -0.23
    âĢ£
    -0.21
    Actualizar
    -0.20
    полниÑĤÑĮ
    -0.20
    iled
    -0.19
    轶
    -0.19
    Contained
    -0.19
    se
    -0.18
    é¢ĺ主
    -0.18
    POSITIVE LOGITS
     neighb
    0.25
     earthqu
    0.25
     ×Ķ×ķ×ĵ
    0.21
    æī¿
    0.21
    umpt
    0.21
     misd
    0.21
    pgsql
    0.21
    å¾ģ
    0.20
    æĬ¥ç¤¾
    0.20
    BuilderInterface
    0.19
    Activations Density 0.001%

    No Known Activations