© 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. 882
    Prev
    Next
    INDEX
    Explanations

    for situations or circumstances

    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
     uniquely
    -0.08
     Separate
    -0.08
     theirs
    -0.08
     rein
    -0.08
     blazing
    -0.08
    efined
    -0.08
     versatile
    -0.08
    .Photo
    -0.08
     vital
    -0.08
    دÙĩ
    -0.08
    POSITIVE LOGITS
     situations
    0.16
     cases
    0.14
     older
    0.13
     circumstances
    0.13
     large
    0.13
     certain
    0.13
     larger
    0.13
     scenarios
    0.12
     when
    0.11
     situation
    0.11
    Activations Density 3.192%

    No Known Activations