© 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. 5001
    Prev
    Next
    INDEX
    Explanations

    commitments and expectations

    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
    osal
    -0.10
    avanaugh
    -0.10
     familiar
    -0.10
    orizontal
    -0.09
    bud
    -0.09
    jet
    -0.09
     Naked
    -0.09
    leans
    -0.09
     usual
    -0.09
     common
    -0.09
    POSITIVE LOGITS
    olio
    0.08
    avo
    0.08
    phin
    0.08
    /prom
    0.08
    abo
    0.08
    Aux
    0.07
    ksam
    0.07
     gridSize
    0.07
     mint
    0.07
     aborted
    0.07
    Activations Density 0.231%

    No Known Activations