© 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. 57356
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

    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
    er
    -0.13
    ive
    -0.10
     powerless
    -0.08
    shaw
    -0.08
    roit
    -0.08
     caramel
    -0.08
    teenth
    -0.08
     shaving
    -0.08
    eron
    -0.07
     fing
    -0.07
    POSITIVE LOGITS
     totalement
    0.09
    vero
    0.08
    .datab
    0.08
    gency
    0.08
    bef
    0.08
    bos
    0.08
    izzie
    0.08
    ique
    0.08
     Lena
    0.08
    adia
    0.08
    Activations Density 0.002%

    No Known Activations