© 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
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 2475
    Prev
    Next
    INDEX
    Explanations

    success and improvement

    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
    @student
    -0.09
    charts
    -0.08
    redo
    -0.08
    unched
    -0.08
     Hue
    -0.08
    .Logic
    -0.07
     Tar
    -0.07
    eto
    -0.07
     Nil
    -0.07
    nable
    -0.07
    POSITIVE LOGITS
    ”:
    0.11
    )):
    0.10
    ]):
    0.10
     Tobias
    0.09
    ’:
    0.09
    ):
    0.09
    ạ
    0.09
     Indeed
    0.09
    :.
    0.09
    аÑģ
    0.09
    Activations Density 0.362%

    No Known Activations