© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116698
    Prev
    Next
    INDEX
    Explanations

    version or qualification

    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
    Not in Any Lists

    No Comments

    Negative Logits
    yaw
    -0.09
    ISCO
    -0.09
    (CC
    -0.09
    108
    -0.09
     Attr
    -0.08
     sexual
    -0.08
     descri
    -0.08
     attr
    -0.08
    aat
    -0.08
    /at
    -0.08
    POSITIVE LOGITS
     inward
    0.10
     jardin
    0.10
     rem
    0.10
    /database
    0.10
     cir
    0.09
     analogue
    0.09
    ira
    0.09
    uplicated
    0.09
    AsStream
    0.09
    .rdf
    0.09
    Activations Density 0.001%

    No Known Activations