© 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. 55070
    Prev
    Next
    INDEX
    Explanations

    although, while, though, because

    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
    ox
    -0.08
     Inn
    -0.07
    Elements
    -0.06
     stad
    -0.06
    los
    -0.06
    yp
    -0.06
     pix
    -0.06
    .ua
    -0.06
    .gdx
    -0.06
    lands
    -0.06
    POSITIVE LOGITS
    eker
    0.11
    achi
    0.10
    ...,
    0.10
    bia
    0.10
    /sources
    0.10
    pit
    0.10
    bons
    0.10
    inde
    0.10
    atted
    0.10
    itized
    0.10
    Activations Density 0.108%

    No Known Activations