© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    same configuration

    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
    eman
    -0.10
    efe
    -0.10
     Josef
    -0.10
    ös
    -0.10
    ksen
    -0.10
     joe
    -0.10
    ixo
    -0.10
    ffe
    -0.09
     instinct
    -0.09
     sut
    -0.09
    POSITIVE LOGITS
     same
    0.17
    same
    0.15
    Same
    0.13
     Same
    0.12
     identical
    0.12
    åIJĮ
    0.10
     SAME
    0.09
    SAME
    0.08
    _same
    0.08
     already
    0.08
    Activations Density 0.406%

    No Known Activations