© 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. 49375
    Prev
    Next
    INDEX
    Explanations

    project

    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
     Nap
    -0.10
    Pow
    -0.09
    ifie
    -0.09
     Trick
    -0.09
    Practice
    -0.09
    hack
    -0.09
     Nuggets
    -0.09
     Practice
    -0.09
    prov
    -0.09
     Technique
    -0.09
    POSITIVE LOGITS
     project
    0.70
    project
    0.51
     Project
    0.50
     projects
    0.49
    Project
    0.47
    -project
    0.46
    é¡¹çĽ®
    0.46
     PROJECT
    0.43
     proj
    0.42
    _project
    0.41
    Activations Density 1.764%

    No Known Activations