© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
     NG
    -0.09
     yourself
    -0.09
     yourselves
    -0.09
     conflic
    -0.09
    requ
    -0.09
    sec
    -0.08
    osh
    -0.08
     frem
    -0.08
     peaked
    -0.08
    vale
    -0.08
    POSITIVE LOGITS
     can
    0.10
     crud
    0.09
     might
    0.08
     Cooke
    0.08
     advisory
    0.08
    adir
    0.08
     need
    0.08
     must
    0.08
     intuit
    0.08
     fist
    0.08
    Activations Density 0.152%

    No Known Activations