© 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. 55487
    Prev
    Next
    INDEX
    Explanations

    Buff followed by ie, alo, eted, or, ers, ile

    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
    ÑĮ
    -0.12
    er
    -0.09
    اس
    -0.09
    ize
    -0.09
     sal
    -0.09
    izing
    -0.08
    reds
    -0.08
    mars
    -0.08
    tes
    -0.08
    seg
    -0.08
    POSITIVE LOGITS
    reich
    0.10
     Eid
    0.09
    ement
    0.09
    e
    0.09
    /he
    0.09
    eid
    0.09
     coh
    0.09
    blr
    0.09
    oon
    0.08
    .dom
    0.08
    Activations Density 0.002%

    No Known Activations