© 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. 1683
    Prev
    Next
    INDEX
    Explanations

    the [technical noun]

    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
    .Never
    -0.09
    eneric
    -0.09
     slic
    -0.09
     doGet
    -0.08
     Ther
    -0.08
     strang
    -0.08
    ÙIJ
    -0.08
    alm
    -0.08
     big
    -0.08
    ymm
    -0.07
    POSITIVE LOGITS
     entire
    0.16
     aforementioned
    0.14
     resulting
    0.13
     resultant
    0.13
     same
    0.13
     newly
    0.12
     offending
    0.12
     remaining
    0.11
     ensuing
    0.10
     actual
    0.10
    Activations Density 1.590%

    No Known Activations