© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ward
    -0.22
    æ¡İ
    -0.20
    åĨį
    -0.20
    ãĤĤãĤĬ
    -0.19
     kang
    -0.19
    _usec
    -0.18
    SharedPtr
    -0.18
    _nsec
    -0.18
    è°¤
    -0.18
    ÏĮ
    -0.18
    POSITIVE LOGITS
    âļĹ
    0.27
     çĶŁåij½åij¨æľŁ
    0.26
    ,},↵
    0.25
    berra
    0.24
    íĶĦë¡ľê·¸
    0.23
    ECTOR
    0.23
    å§Ķç»Ħç»ĩ
    0.22
    -END
    0.22
    éĶ¦æłĩ
    0.21
    MSN
    0.21
    Activations Density 0.004%

    No Known Activations