© 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. 204
    Prev
    Next
    INDEX
    Explanations

    programming 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
     taraf
    -0.26
     resil
    -0.23
    getSingleton
    -0.22
     suscept
    -0.22
     slog
    -0.22
     gravid
    -0.21
     hoodie
    -0.21
    ;!
    -0.21
    ÑĤеÑħнолог
    -0.21
    o
    -0.21
    POSITIVE LOGITS
    对çħ§æ£ĢæŁ¥
    0.26
     bénéficie
    0.25
    ÑīиÑĤ
    0.25
    æĦıè§ģåıįé¦Ī
    0.25
    :both
    0.24
    classed
    0.24
    å§ĭ建
    0.24
    缸åħ³è´Łè´£
    0.24
    greSQL
    0.23
    AndView
    0.23
    Activations Density 0.135%

    No Known Activations