© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3242
    Prev
    Next
    INDEX
    Explanations

    temporal or locational context

    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
    ocs
    -0.11
    ɵ
    -0.10
    aces
    -0.09
    ICI
    -0.09
    antal
    -0.09
    arts
    -0.09
    gard
    -0.09
    oins
    -0.09
    izada
    -0.09
    ACE
    -0.09
    POSITIVE LOGITS
     saf
    0.08
     rather
    0.08
     individual
    0.08
     op
    0.08
     próp
    0.07
     ticket
    0.07
     und
    0.07
    ts
    0.07
    pes
    0.07
     Op
    0.07
    Activations Density 0.359%

    No Known Activations