© 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. 952
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
    umo
    -0.15
     briefly
    -0.13
    ardy
    -0.12
     plutôt
    -0.11
     equally
    -0.11
    zig
    -0.11
     quicker
    -0.11
    plusplus
    -0.11
    ç¨į
    -0.11
     slightly
    -0.11
    POSITIVE LOGITS
     (>
    0.22
     (~
    0.14
     compared
    0.14
     indeed
    0.13
     lately
    0.10
    Indeed
    0.09
     Indeed
    0.09
    (~
    0.09
     imaginable
    0.08
     both
    0.08
    Activations Density 3.156%

    No Known Activations