© 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. 116074
    Prev
    Next
    INDEX
    Explanations

    bonus award or extra

    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
    stone
    -0.12
    (<
    -0.10
    ges
    -0.10
    anske
    -0.10
    ipo
    -0.10
     superiority
    -0.10
    env
    -0.10
    ta
    -0.10
    hone
    -0.10
     ^(
    -0.10
    POSITIVE LOGITS
    alus
    0.08
     extras
    0.08
     awarded
    0.08
    ť
    0.08
    fib
    0.07
    /pre
    0.07
     attendance
    0.07
    -winning
    0.07
    ieurs
    0.07
     Marl
    0.07
    Activations Density 0.022%

    No Known Activations