© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2867
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ân
    -0.11
    .series
    -0.09
     wiel
    -0.09
    ODY
    -0.09
    -bin
    -0.09
    еÑĪ
    -0.09
    izar
    -0.09
    igt
    -0.09
     Perc
    -0.08
    ug
    -0.08
    POSITIVE LOGITS
     Sto
    0.08
     bump
    0.07
     assort
    0.07
    acc
    0.07
    enis
    0.07
     faces
    0.07
     callbacks
    0.07
    -su
    0.07
    arent
    0.07
    aksi
    0.07
    Activations Density 0.018%

    No Known Activations