© 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. 2860
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    -awesome
    -0.21
    rees
    -0.21
    碹
    -0.20
    berapa
    -0.20
     :";↵
    -0.19
    游æĪıå½ĵä¸Ń
    -0.19
    椽
    -0.18
    .Protocol
    -0.18
    .LayoutStyle
    -0.18
     ($.
    -0.18
    POSITIVE LOGITS
     Hayden
    0.19
    墦
    0.19
    razier
    0.19
     Conor
    0.19
     particulière
    0.19
     résult
    0.18
     Kardash
    0.18
    .EventQueue
    0.18
    éĤĹ
    0.18
     OMIT
    0.18
    Activations Density 0.035%

    No Known Activations