© 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. 112771
    Prev
    Next
    INDEX
    Explanations

    I don't care

    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
     Wald
    -0.14
     kal
    -0.14
    omp
    -0.11
    KER
    -0.10
    Ignore
    -0.10
     pendant
    -0.10
    izzo
    -0.10
    kal
    -0.10
     gust
    -0.10
    MAND
    -0.10
    POSITIVE LOGITS
     anymore
    0.11
     about
    0.09
     immensely
    0.08
     invalidated
    0.08
    borg
    0.07
    fin
    0.07
    beans
    0.07
     Fridays
    0.07
    yen
    0.07
     ADM
    0.07
    Activations Density 0.005%

    No Known Activations