© 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. 56704
    Prev
    Next
    INDEX
    Explanations

    notes and warnings

    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
     ter
    -0.12
    LBL
    -0.11
     gr
    -0.11
    Ide
    -0.10
     Ter
    -0.10
     {↵↵↵↵
    -0.10
    bes
    -0.10
    lets
    -0.10
    orts
    -0.10
    .utilities
    -0.10
    POSITIVE LOGITS
    ue
    0.07
     Gunn
    0.07
    merc
    0.07
    HS
    0.06
    dia
    0.06
    985
    0.06
     wildly
    0.06
    phony
    0.06
     whichever
    0.06
    fuse
    0.05
    Activations Density 0.001%

    No Known Activations