© 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. 842
    Prev
    Next
    INDEX
    Explanations

    in addition to

    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
     _______,
    -0.15
    ...,
    -0.15
    ,...↵
    -0.14
    (""),
    -0.14
     (),
    -0.13
    !,
    -0.13
     zwar
    -0.13
    ,[
    -0.12
    ,,
    -0.12
    !),
    -0.12
    POSITIVE LOGITS
    .↵↵
    0.17
    %.↵↵
    0.15
    ãĢĤ↵↵
    0.14
     .↵↵
    0.13
    .↵
    0.13
     otherwise
    0.12
    .
    0.12
    `.↵↵
    0.12
    ãĢĤ
    0.12
    ().
    0.12
    Activations Density 9.961%

    No Known Activations