© 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. 50621
    Prev
    Next
    INDEX
    Explanations

    story highlights or excerpt

    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
    istrator
    -0.11
    /bus
    -0.10
     Epoch
    -0.10
    TING
    -0.10
    endon
    -0.10
    stre
    -0.10
    ï¸ı
    -0.10
    iment
    -0.10
     Firm
    -0.10
    ala
    -0.10
    POSITIVE LOGITS
    lines
    0.20
    boards
    0.18
     arc
    0.15
    boarding
    0.15
    book
    0.15
     arcs
    0.11
    arc
    0.11
    line
    0.11
    atics
    0.11
    board
    0.11
    Activations Density 0.118%

    No Known Activations