© 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. 25741
    Prev
    Next
    INDEX
    Explanations

    end of

    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
     Finish
    -0.13
     later
    -0.12
    fund
    -0.12
     Way
    -0.12
    Finish
    -0.11
     Zug
    -0.11
     finish
    -0.11
     dern
    -0.11
    iew
    -0.11
     elsewhere
    -0.11
    POSITIVE LOGITS
     involvement
    0.10
     matter
    0.09
     regards
    0.08
     regard
    0.08
     matters
    0.08
     similarities
    0.08
     antic
    0.07
     extent
    0.07
    ope
    0.07
     similarity
    0.07
    Activations Density 0.025%

    No Known Activations