© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    re- prefix for 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
    ta
    -0.14
    ts
    -0.13
    tes
    -0.13
    tt
    -0.12
    tn
    -0.12
    ly
    -0.12
    ths
    -0.11
    ting
    -0.11
    ters
    -0.11
    to
    -0.11
    POSITIVE LOGITS
    edException
    0.11
    oons
    0.10
    .self
    0.10
    alth
    0.10
    IEW
    0.10
    /sub
    0.10
    leigh
    0.09
    hee
    0.09
    uali
    0.09
    etwork
    0.09
    Activations Density 0.040%

    No Known Activations