© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56186
    Prev
    Next
    INDEX
    Explanations

    I'm impressed by that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     folks
    -0.10
     darn
    -0.10
    eren
    -0.07
    cou
    -0.07
     beaut
    -0.07
    lass
    -0.07
    udi
    -0.07
    uft
    -0.07
     Bi
    -0.07
    ict
    -0.06
    POSITIVE LOGITS
     luckily
    0.12
    (..
    0.11
    AtA
    0.11
    Uvs
    0.10
    @media
    0.10
     Dip
    0.10
    :["
    0.10
     Wallpaper
    0.10
     masturbating
    0.10
    (()=>
    0.10
    Activations Density 0.027%

    No Known Activations