© 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. 49201
    Prev
    Next
    INDEX
    Explanations

    At least

    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
    eld
    -0.09
    gb
    -0.09
    utils
    -0.09
     Hur
    -0.09
    uru
    -0.09
     wi
    -0.09
     weekends
    -0.09
     Ere
    -0.09
    iol
    -0.08
    231
    -0.08
    POSITIVE LOGITS
     Leh
    0.10
    -le
    0.10
    gard
    0.09
    reinterpret
    0.09
    lest
    0.09
     bearing
    0.09
    bak
    0.08
     least
    0.08
     ripe
    0.08
    inary
    0.08
    Activations Density 0.100%

    No Known Activations