© 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. 114908
    Prev
    Next
    INDEX
    Explanations

    usage and rights

    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
    lessness
    -0.15
    nings
    -0.12
    ings
    -0.11
    house
    -0.11
    line
    -0.10
    cases
    -0.10
    paths
    -0.10
    hw
    -0.09
    lessly
    -0.09
    holders
    -0.09
    POSITIVE LOGITS
    /Application
    0.10
    /terms
    0.10
     lit
    0.10
    elan
    0.09
    itarian
    0.09
    itar
    0.09
     bre
    0.09
    izen
    0.09
    eko
    0.09
    icode
    0.08
    Activations Density 0.030%

    No Known Activations