© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90122
    Prev
    Next
    INDEX
    Explanations

    J names or initials

    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
     Rory
    -0.10
    argo
    -0.09
     handc
    -0.09
     Gale
    -0.09
    _pct
    -0.09
     Boulder
    -0.09
     PAC
    -0.09
    ank
    -0.09
     Fi
    -0.08
    Tes
    -0.08
    POSITIVE LOGITS
    jas
    0.11
    tin
    0.10
     bloody
    0.09
    adin
    0.09
    asper
    0.09
     dismal
    0.09
     Shannon
    0.09
     shim
    0.09
    onen
    0.09
     JM
    0.09
    Activations Density 0.001%

    No Known Activations