© 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. 53910
    Prev
    Next
    INDEX
    Explanations

    45 minutes

    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
    eral
    -0.11
    cr
    -0.08
    ORY
    -0.08
    por
    -0.08
    lander
    -0.08
    icode
    -0.07
    eus
    -0.07
    usting
    -0.07
    fram
    -0.07
    nio
    -0.07
    POSITIVE LOGITS
    zi
    0.11
    omin
    0.10
    volution
    0.10
    ÑģÑı
    0.10
    borg
    0.09
    IONS
    0.09
    lys
    0.09
     conquer
    0.09
    /material
    0.09
    stands
    0.09
    Activations Density 0.010%

    No Known Activations