© 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. 91074
    Prev
    Next
    INDEX
    Explanations

    hopeful predictions

    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
     assured
    -0.12
     reportedly
    -0.10
     plenty
    -0.10
     enormously
    -0.10
     Dress
    -0.10
     certainly
    -0.09
     assurance
    -0.09
    quite
    -0.09
     Plenty
    -0.09
     impecc
    -0.09
    POSITIVE LOGITS
     somehow
    0.30
     someday
    0.20
     somew
    0.20
     luck
    0.18
     Somehow
    0.17
     magically
    0.17
     lucky
    0.16
     salvage
    0.16
     mirac
    0.16
     somewhere
    0.15
    Activations Density 0.127%

    No Known Activations