© 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. 90130
    Prev
    Next
    INDEX
    Explanations

    awards and evaluations

    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
     Rescue
    -0.08
    {"
    -0.08
     constellation
    -0.08
    osp
    -0.08
    pell
    -0.08
    ubber
    -0.08
    pit
    -0.08
    ismo
    -0.08
     benches
    -0.08
     appell
    -0.08
    POSITIVE LOGITS
     lump
    0.12
    ova
    0.11
    bung
    0.10
    sla
    0.10
    ühl
    0.10
    onta
    0.10
     lokale
    0.10
     disg
    0.10
    indr
    0.09
     hookers
    0.09
    Activations Density 0.001%

    No Known Activations