© 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. 259
    Prev
    Next
    INDEX
    Explanations

    material consumption, materials exhibiting, material UI, materials provided

    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
    es
    -0.11
    adel
    -0.09
    kos
    -0.09
     Bellev
    -0.09
    ай
    -0.09
    ees
    -0.09
    Ñģл
    -0.09
    alty
    -0.09
    kaar
    -0.08
    rees
    -0.08
    POSITIVE LOGITS
    ity
    0.17
    istic
    0.14
    æĸĻ
    0.14
    istically
    0.11
    (Material
    0.11
    ism
    0.10
    ien
    0.10
    ize
    0.10
    (material
    0.10
    horn
    0.10
    Activations Density 0.407%

    No Known Activations