© 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. 26810
    Prev
    Next
    INDEX
    Explanations

    I am/have/know/just

    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
    ivi
    -0.10
     Kut
    -0.10
    /Q
    -0.09
    azen
    -0.09
    itten
    -0.09
     otherwise
    -0.09
     rit
    -0.09
    प
    -0.09
     Bud
    -0.09
     Fountain
    -0.09
    POSITIVE LOGITS
     hope
    0.11
     thought
    0.10
     brib
    0.10
     hoped
    0.10
     today
    0.10
     empir
    0.10
     Heard
    0.10
     heard
    0.09
     finished
    0.09
     wondered
    0.09
    Activations Density 0.054%

    No Known Activations