© 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. 131
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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
    (targetEntity
    -0.22
     Ly
    -0.20
     obvious
    -0.20
    æ¸į
    -0.20
     familiar
    -0.19
    ]+\
    -0.19
    .removeItem
    -0.19
    bung
    -0.19
     univers
    -0.19
     beyond
    -0.19
    POSITIVE LOGITS
    çݩ家æľĭåıĭ
    0.26
     cigaret
    0.25
    æķī
    0.23
     Www
    0.23
     indeb
    0.23
    CLOCKS
    0.22
    UEL
    0.22
     iParam
    0.22
     Rencontre
    0.21
    +'&
    0.21
    Activations Density 0.001%

    No Known Activations