© 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. 2897
    Prev
    Next
    INDEX
    Explanations

    percentages after counts

    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
    RU
    -0.09
    (that
    -0.08
    gear
    -0.08
    éĻĨ
    -0.08
     plugs
    -0.08
     floating
    -0.08
     flotation
    -0.08
    RP
    -0.08
    SV
    -0.08
     bluff
    -0.08
    POSITIVE LOGITS
     remaining
    0.18
     remainder
    0.17
    remaining
    0.16
    Remaining
    0.16
     Remaining
    0.16
    _remaining
    0.14
    .remaining
    0.13
    remainder
    0.12
     rest
    0.12
     Remain
    0.11
    Activations Density 0.140%

    No Known Activations