© 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. 114549
    Prev
    Next
    INDEX
    Explanations

    drawing

    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
    аем
    -0.11
    /of
    -0.10
    emit
    -0.10
    indr
    -0.09
    ä
    -0.09
     Gratuit
    -0.09
    gross
    -0.09
     tread
    -0.09
    ally
    -0.09
    TING
    -0.09
    POSITIVE LOGITS
    backs
    0.17
     attention
    0.13
     parallels
    0.11
    down
    0.11
    /render
    0.11
    -out
    0.11
     conclusions
    0.11
    paralle
    0.11
    back
    0.10
     Attention
    0.10
    Activations Density 0.064%

    No Known Activations