© 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. 89598
    Prev
    Next
    INDEX
    Explanations

    130 or 129 context

    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
    itr
    -0.12
    iaz
    -0.11
    ial
    -0.11
    iel
    -0.10
    nable
    -0.10
     perfect
    -0.10
    ares
    -0.10
    nder
    -0.10
    iem
    -0.10
    iced
    -0.10
    POSITIVE LOGITS
     Stranger
    0.08
     stranger
    0.08
    ocab
    0.08
    wrap
    0.08
    izen
    0.08
    boxing
    0.08
     Worst
    0.07
    dden
    0.07
    ëł¥
    0.07
    ocate
    0.07
    Activations Density 0.124%

    No Known Activations