© 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. 58811
    Prev
    Next
    INDEX
    Explanations

    human rights

    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
     humans
    -0.11
     human
    -0.10
    Humans
    -0.07
     Bra
    -0.07
     Humans
    -0.07
     Homo
    -0.07
    gan
    -0.07
    SEM
    -0.07
    uthor
    -0.07
     naturally
    -0.06
    POSITIVE LOGITS
    eto
    0.12
     mou
    0.11
    iki
    0.11
    /pages
    0.11
    ix
    0.11
    istic
    0.11
     fel
    0.10
     hog
    0.10
     fec
    0.10
    832
    0.10
    Activations Density 0.016%

    No Known Activations