© 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. 4859
    Prev
    Next
    INDEX
    Explanations

    .com domain names

    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
    borg
    -0.10
    ofile
    -0.09
     Scient
    -0.09
    esion
    -0.09
    thal
    -0.09
    è§Ĵ
    -0.08
    rug
    -0.08
    lemn
    -0.08
    ait
    -0.08
    lems
    -0.08
    POSITIVE LOGITS
    .au
    0.09
    ix
    0.08
    iris
    0.08
    cole
    0.07
    .ua
    0.07
    tingham
    0.07
     Gore
    0.06
    iore
    0.06
     Bott
    0.06
    uentes
    0.06
    Activations Density 0.073%

    No Known Activations