© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    in part or participate

    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
     whereas
    -0.11
     inse
    -0.11
    _=
    -0.11
     //-
    -0.10
    .).
    -0.10
    youtu
    -0.10
    ":{"
    -0.10
    _("
    -0.10
    âĨIJ
    -0.10
     };↵↵↵
    -0.10
    POSITIVE LOGITS
     import
    0.07
    (cls
    0.06
    kre
    0.06
     tamb
    0.06
     isempty
    0.06
     nau
    0.06
    /cmd
    0.06
    #endregion
    0.06
     trous
    0.06
    (self
    0.06
    Activations Density 3.305%

    No Known Activations