© 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. 7473
    Prev
    Next
    INDEX
    Explanations

    license

    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
     Swing
    -0.11
     Pocket
    -0.10
     literally
    -0.10
     legitimately
    -0.10
    leck
    -0.10
    hone
    -0.10
    ulent
    -0.10
     profit
    -0.09
     prized
    -0.09
     arbit
    -0.09
    POSITIVE LOGITS
     afterward
    0.11
     afterwards
    0.10
     Afterwards
    0.09
    Expiration
    0.09
    ohl
    0.09
     bleach
    0.09
     preferably
    0.09
     firstly
    0.08
    aseline
    0.08
     discrepan
    0.08
    Activations Density 0.002%

    No Known Activations