© 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. 47853
    Prev
    Next
    INDEX
    Explanations

    or and /or

    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
     booklet
    -0.10
     irres
    -0.09
     pressures
    -0.09
     Chili
    -0.09
    edm
    -0.09
    chen
    -0.09
     EXTRA
    -0.09
     amateurs
    -0.09
    ir
    -0.09
     irr
    -0.09
    POSITIVE LOGITS
     support
    0.13
     publicity
    0.10
     insurance
    0.10
     public
    0.10
     manpower
    0.09
    chez
    0.09
    ICO
    0.09
     erect
    0.09
     Support
    0.09
     respect
    0.09
    Activations Density 0.001%

    No Known Activations