© 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. 4387
    Prev
    Next
    INDEX
    Explanations

    agreement or acknowledgement

    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
     Imper
    -0.10
     handy
    -0.10
     Sofa
    -0.09
     internals
    -0.09
    ò
    -0.09
    hev
    -0.09
     Absolutely
    -0.09
    omp
    -0.09
     Johnston
    -0.09
    rio
    -0.09
    POSITIVE LOGITS
     alright
    0.16
    Alright
    0.16
     fine
    0.16
     Fine
    0.15
     okay
    0.15
    Fine
    0.15
    fine
    0.14
     Alright
    0.13
    okay
    0.13
     Okay
    0.13
    Activations Density 0.076%

    No Known Activations