© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8449
    Prev
    Next
    INDEX
    Explanations

    modal verbs and requirements

    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
    ients
    -0.13
    anske
    -0.11
    ...↵↵↵↵
    -0.11
    woke
    -0.10
    lined
    -0.10
    amba
    -0.10
    ulis
    -0.10
    ended
    -0.10
    urch
    -0.10
    kan
    -0.10
    POSITIVE LOGITS
    tas
    0.07
    ux
    0.07
    nt
    0.07
     NOT
    0.07
     happen
    0.06
    iard
    0.06
    mom
    0.06
     relative
    0.06
    098
    0.06
    ç»ı
    0.06
    Activations Density 0.273%

    No Known Activations