© 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. 8125
    Prev
    Next
    INDEX
    Explanations

    accompanying materials, license

    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
     Sidd
    -0.08
     pil
    -0.08
     Hack
    -0.08
    UA
    -0.08
    GU
    -0.08
    irth
    -0.07
    alia
    -0.07
    ..
    -0.07
     jest
    -0.07
    idding
    -0.07
    POSITIVE LOGITS
     Mag
    0.10
    iph
    0.09
    mag
    0.09
    stral
    0.09
    iec
    0.09
     McGr
    0.08
    (fabs
    0.08
    sep
    0.08
     Accum
    0.08
    lav
    0.08
    Activations Density 0.322%

    No Known Activations