© 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. 114427
    Prev
    Next
    INDEX
    Explanations

    Bot configs, Nicholas, Yes, Friend, discount, ubuntu, cranial

    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
    papers
    -0.09
     depr
    -0.09
    numer
    -0.09
    inne
    -0.09
    agine
    -0.09
    gue
    -0.09
    renal
    -0.08
    arm
    -0.08
     recomm
    -0.08
    kart
    -0.08
    POSITIVE LOGITS
     accessor
    0.09
     Monad
    0.08
    burg
    0.08
     slump
    0.08
     roughly
    0.08
     crossover
    0.08
     towers
    0.08
     ÑĤоÑĩ
    0.08
     topo
    0.08
     lawy
    0.08
    Activations Density 0.001%

    No Known Activations