© 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. 53745
    Prev
    Next
    INDEX
    Explanations

    names after actions or speech

    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
    ctl
    -0.09
    iere
    -0.09
    iol
    -0.09
    tas
    -0.09
     Secure
    -0.09
    rack
    -0.09
    onn
    -0.08
    esi
    -0.08
     Adam
    -0.08
    orte
    -0.08
    POSITIVE LOGITS
     Astro
    0.08
     and
    0.08
     abducted
    0.08
    shi
    0.07
    arde
    0.07
    /student
    0.07
     insulated
    0.07
     repeatedly
    0.07
    /cop
    0.07
    chap
    0.07
    Activations Density 0.002%

    No Known Activations