© 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. 1640
    Prev
    Next
    INDEX
    Explanations

    combination strategies

    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
     Äijá»ĥ
    -0.10
     ÑĩÑĤобÑĭ
    -0.10
     useful
    -0.10
    пиÑģание
    -0.10
    .PrimaryKey
    -0.10
    spa
    -0.10
    aset
    -0.10
    zza
    -0.10
    isser
    -0.09
    ...");↵↵
    -0.09
    POSITIVE LOGITS
     alone
    0.13
     combination
    0.11
     careful
    0.10
    combination
    0.10
     carefully
    0.10
     combined
    0.10
     Alone
    0.10
    alone
    0.09
     appropriately
    0.09
     either
    0.09
    Activations Density 3.573%

    No Known Activations