© 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. 113575
    Prev
    Next
    INDEX
    Explanations

    assuming and multiplying

    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
     banc
    -0.12
    kal
    -0.11
    ohl
    -0.10
    pite
    -0.10
    rais
    -0.10
    adi
    -0.09
    bose
    -0.09
    .sw
    -0.09
     Sit
    -0.09
    ecom
    -0.09
    POSITIVE LOGITS
     Assuming
    0.25
     assuming
    0.24
     multiplied
    0.22
     multiply
    0.22
     assume
    0.21
     Assume
    0.21
     assumed
    0.20
    assuming
    0.20
     multiplying
    0.20
     assumptions
    0.20
    Activations Density 0.203%

    No Known Activations