© 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. 8293
    Prev
    Next
    INDEX
    Explanations

    Smith 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
    eg
    -0.09
    ellan
    -0.09
    oter
    -0.09
    ly
    -0.08
     bueno
    -0.08
     qua
    -0.08
    oine
    -0.08
    ei
    -0.08
    igner
    -0.08
    er
    -0.08
    POSITIVE LOGITS
    hood
    0.09
    asses
    0.09
    /rec
    0.08
     informat
    0.08
     foss
    0.08
    otp
    0.08
    arming
    0.08
    bounding
    0.08
     Rudy
    0.08
    atical
    0.08
    Activations Density 0.249%

    No Known Activations