© 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. 173
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    *****↵↵
    -0.24
    :".$
    -0.24
    gnore
    -0.24
    )":
    -0.23
    èĵĬ
    -0.23
    黩
    -0.22
     èĩªåĬ¨çĶŁæĪIJ
    -0.22
    BASEPATH
    -0.22
    ]';↵
    -0.21
    ORLD
    -0.21
    POSITIVE LOGITS
     copyright
    0.29
    ogenerated
    0.28
     Copyright
    0.27
    copyright
    0.24
     copyrights
    0.24
    ä»ħä¾ĽåıĤèĢĥ
    0.24
    Copyright
    0.23
     revision
    0.21
    	This
    0.21
    -abortion
    0.21
    Activations Density 3.435%

    No Known Activations