© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 58956
    Prev
    Next
    INDEX
    Explanations

    techno-

    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
    Negative Logits
    ty
    -0.10
    uration
    -0.10
    ron
    -0.09
    -0.09
    tures
    -0.09
    ting
    -0.08
    evity
    -0.08
    lace
    -0.08
     Swagger
    -0.08
    don
    -0.08
    POSITIVE LOGITS
    ically
    0.13
    ic
    0.13
    etwork
    0.11
    eses
    0.11
    ally
    0.10
    ICA
    0.10
    icolor
    0.09
    ADA
    0.09
    -ng
    0.09
    ics
    0.09
    Activations Density 0.005%

    No Known Activations