© 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. 58785
    Prev
    Next
    INDEX
    Explanations

    contracts, use, dark, action, pm, abortions

    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
     freely
    -0.11
    imas
    -0.10
     illegally
    -0.10
     pir
    -0.10
     liberty
    -0.09
     unauthorized
    -0.09
     liberties
    -0.09
     Forbidden
    -0.09
     risky
    -0.09
     Norm
    -0.09
    POSITIVE LOGITS
     except
    0.09
    oya
    0.08
     Ember
    0.08
    ocal
    0.08
     Barth
    0.08
    icens
    0.08
    eca
    0.08
    dap
    0.08
    asc
    0.08
    arus
    0.08
    Activations Density 0.041%

    No Known Activations