© 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. 55137
    Prev
    Next
    INDEX
    Explanations

    numbers, loop indices, code snippets

    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
     (>
    -0.10
     scl
    -0.09
    omas
    -0.09
    ateur
    -0.09
     prise
    -0.09
     allowable
    -0.09
     Iz
    -0.08
     Bundle
    -0.08
    ellow
    -0.08
     Ib
    -0.08
    POSITIVE LOGITS
    chy
    0.09
    ouse
    0.09
    land
    0.08
     endings
    0.08
    inyin
    0.08
     hal
    0.08
    born
    0.08
    cent
    0.08
    .kr
    0.08
    achable
    0.08
    Activations Density 0.056%

    No Known Activations