© 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. 32380
    Prev
    Next
    INDEX
    Explanations

    code syntax components

    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
     Dwarf
    -0.10
    ¯
    -0.09
    iete
    -0.09
     afforded
    -0.09
     apro
    -0.09
     dist
    -0.08
    lep
    -0.08
     metab
    -0.08
     vanity
    -0.08
     rehabilit
    -0.08
    POSITIVE LOGITS
     Bust
    0.09
     Lis
    0.09
     treasure
    0.08
     ratified
    0.08
     vielen
    0.08
     prosecuted
    0.08
    âĶģ
    0.08
     tact
    0.08
    chest
    0.08
    anker
    0.08
    Activations Density 0.001%

    No Known Activations