© 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. 4690
    Prev
    Next
    INDEX
    Explanations

    controller, service, rule, page

    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
     Pac
    -0.09
     beg
    -0.06
     inst
    -0.06
     Hew
    -0.06
     quint
    -0.06
    APE
    -0.06
    owe
    -0.06
    .hasOwnProperty
    -0.06
     minded
    -0.06
     forged
    -0.06
    POSITIVE LOGITS
    )r
    0.11
     Near
    0.10
    eden
    0.10
    UCH
    0.10
    .CopyTo
    0.09
    rador
    0.09
    Teams
    0.09
    INET
    0.09
    sa
    0.09
    Santa
    0.09
    Activations Density 0.129%

    No Known Activations