© 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. 718
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    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
    âĺ°
    -0.31
    à¸ľà¸¡
    -0.29
    èĥ¨
    -0.26
     vbCrLf
    -0.26
     "";č↵č↵
    -0.25
    æĪijãĢħ
    -0.25
     Ä°stanbul
    -0.23
    âĩĭ
    -0.23
    æľĭåıĭ们对
    -0.23
    å¼Ģå¥ĸç»ĵæŀľ
    -0.23
    POSITIVE LOGITS
    éĩĩçŁ¿çŃī
    0.31
     maneu
    0.31
     burge
    0.28
    ḡ
    0.27
    theless
    0.26
     Pinterest
    0.25
    ].'
    0.24
    åħļæĢ»
    0.23
    birthdate
    0.23
    .easing
    0.23
    Activations Density 6.265%

    No Known Activations