© 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. 3436
    Prev
    Next
    INDEX
    Explanations

    Madagascar

    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
     Kurdish
    -0.12
     Maced
    -0.12
     Sü
    -0.10
     Klo
    -0.09
    SCO
    -0.09
     tempor
    -0.09
     Alta
    -0.09
    chai
    -0.09
     Sai
    -0.09
    ám
    -0.09
    POSITIVE LOGITS
     Madagascar
    0.22
    à·
    0.16
    à¶
    0.15
     ejected
    0.13
     Rand
    0.13
     Maurit
    0.12
     Lanka
    0.12
     à
    0.12
     Newark
    0.12
     lem
    0.12
    Activations Density 0.453%

    No Known Activations