© 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. 14736
    Prev
    Next
    INDEX
    Explanations

    then followed by a clause or question

    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
     therefore
    -0.15
     then
    -0.11
    oft
    -0.10
     Therefore
    -0.10
     daher
    -0.10
     thereafter
    -0.10
     Holden
    -0.10
    Then
    -0.10
     entonces
    -0.10
     Then
    -0.10
    POSITIVE LOGITS
    umi
    0.10
     logically
    0.10
    uhl
    0.10
     since
    0.09
    ey
    0.09
     upset
    0.09
    urple
    0.09
     suit
    0.09
    ?
    0.09
     synerg
    0.09
    Activations Density 0.009%

    No Known Activations