© 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. 3192
    Prev
    Next
    INDEX
    Explanations

    specific subjects

    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
    Ltd
    -0.20
    _xor
    -0.19
    æ·Ļ
    -0.19
    BuilderInterface
    -0.19
    atr
    -0.19
    æĺ¯ä¸Ģ家
    -0.18
    classed
    -0.18
    çłĶ究ä¸Ńå¿ĥ
    -0.18
     realpath
    -0.18
    (milliseconds
    -0.18
    POSITIVE LOGITS
    ãĤĴè¶ħãģĪ
    0.22
    exampleInput
    0.22
     Atat
    0.21
    ĸī
    0.20
    女æĢ§æľĭåıĭ
    0.20
    QDebug
    0.19
    ceptar
    0.19
    bellion
    0.19
     Kardash
    0.19
    uchen
    0.19
    Activations Density 0.001%

    No Known Activations