© 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. 1170
    Prev
    Next
    INDEX
    Explanations

    license distribution

    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
    ality
    -0.09
     sorts
    -0.09
    ous
    -0.09
    ãĥij
    -0.09
    People
    -0.09
     fr
    -0.08
    Pl
    -0.08
    ors
    -0.08
    Pi
    -0.08
    rez
    -0.08
    POSITIVE LOGITS
    hits
    0.09
     MERCHANTABILITY
    0.08
    .openapi
    0.08
    vertise
    0.07
     foregoing
    0.07
    portun
    0.07
    ozy
    0.07
    -pt
    0.07
     krist
    0.07
    .Lo
    0.07
    Activations Density 2.650%

    No Known Activations