© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5884
    Prev
    Next
    INDEX
    Explanations

    month or year qualifiers

    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
    atu
    -0.09
    ishi
    -0.08
     Kut
    -0.08
     CSI
    -0.08
     radi
    -0.07
    IFE
    -0.07
    afd
    -0.07
     Junk
    -0.07
    apiro
    -0.07
    .space
    -0.07
    POSITIVE LOGITS
    -long
    0.25
    long
    0.19
    -old
    0.16
    -ahead
    0.15
    spent
    0.14
     long
    0.14
    -wide
    0.14
    -end
    0.14
    -ending
    0.13
    -by
    0.13
    Activations Density 0.123%

    No Known Activations