© 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. 49395
    Prev
    Next
    INDEX
    Explanations

    finished or completed

    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
     entering
    -0.11
    enter
    -0.11
     enter
    -0.11
     current
    -0.11
     captured
    -0.10
    current
    -0.10
     enters
    -0.10
     approaching
    -0.10
     incoming
    -0.10
     Enter
    -0.10
    POSITIVE LOGITS
     lengthy
    0.10
    ampa
    0.09
     workout
    0.09
    owane
    0.09
     Kes
    0.09
    åıĤ
    0.09
    zm
    0.09
     lac
    0.09
    oli
    0.09
    ERO
    0.09
    Activations Density 0.041%

    No Known Activations