© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50896
    Prev
    Next
    INDEX
    Explanations

    ML, immunisation, major, special

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ageing
    -0.11
     aging
    -0.11
     Aging
    -0.11
    ifen
    -0.10
     Invite
    -0.10
     Sexy
    -0.09
     aged
    -0.09
    !!");↵
    -0.09
    aged
    -0.09
    ady
    -0.09
    POSITIVE LOGITS
     languages
    0.13
     Languages
    0.12
    Languages
    0.10
     contra
    0.10
     preferred
    0.10
     brief
    0.09
     pier
    0.09
     langu
    0.09
    ALT
    0.09
     Astro
    0.09
    Activations Density 0.010%

    No Known Activations