© 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. 17700
    Prev
    Next
    INDEX
    Explanations

    a bit, a little, a touch

    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
    perf
    -0.11
    ptions
    -0.10
    -less
    -0.10
    IMS
    -0.09
     tant
    -0.09
    -render
    -0.09
     alo
    -0.09
    ings
    -0.09
    zac
    -0.09
     visit
    -0.09
    POSITIVE LOGITS
     bit
    0.14
     tad
    0.13
    irt
    0.10
     slog
    0.10
    ight
    0.10
     mix
    0.10
     waste
    0.10
     outlier
    0.09
     pity
    0.09
    tractive
    0.09
    Activations Density 0.277%

    No Known Activations