© 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. 116212
    Prev
    Next
    INDEX
    Explanations

    license, ePub, price, presentation, series, design

    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
    ?↵↵↵↵
    -0.11
    :]↵↵
    -0.11
    ?'↵↵
    -0.10
     за
    -0.10
     sprung
    -0.10
    :č↵č↵
    -0.10
    idden
    -0.10
    alone
    -0.10
     younger
    -0.10
     finance
    -0.10
    POSITIVE LOGITS
     Demp
    0.08
    aight
    0.08
    lets
    0.08
    esi
    0.07
     Mos
    0.07
    porter
    0.07
    quires
    0.07
    wich
    0.07
    ande
    0.07
    inox
    0.07
    Activations Density 0.069%

    No Known Activations