© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
    yper
    -0.24
    微软éĽħé»ij
    -0.23
    :frame
    -0.23
    #aa
    -0.22
    íĺĶ
    -0.21
     Wäh
    -0.21
    以人æ°ij为
    -0.21
    :numel
    -0.21
    vê
    -0.20
    ouro
    -0.20
    POSITIVE LOGITS
    Schedulers
    0.23
    鼶éĥ¨ä»¶
    0.20
    tfoot
    0.20
    .opensource
    0.20
     Aerospace
    0.19
     GPLv
    0.19
    íĶĦë¡ľê·¸
    0.19
    0.19
     -------------------------------------------------------------------------
    0.19
    embourg
    0.19
    Activations Density 0.034%

    No Known Activations