© 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. 27879
    Prev
    Next
    INDEX
    Explanations

    Mozilla Public License

    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
    alie
    -0.09
     nv
    -0.08
    Pink
    -0.08
     Middleton
    -0.08
    CDF
    -0.08
     mess
    -0.08
    parator
    -0.08
     exporting
    -0.08
     NONINFRINGEMENT
    -0.08
     Dub
    -0.08
    POSITIVE LOGITS
     Brewer
    0.10
     Barg
    0.09
     hur
    0.08
     spr
    0.08
    IDX
    0.08
    upo
    0.08
     Confeder
    0.08
     obt
    0.08
     Bis
    0.08
    -wow
    0.08
    Activations Density 3.234%

    No Known Activations