© 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. 49509
    Prev
    Next
    INDEX
    Explanations

    when/during/following + noun

    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
    iska
    -0.10
     curious
    -0.10
     mortal
    -0.10
     compliment
    -0.09
     bisher
    -0.09
     Grad
    -0.09
     triumph
    -0.09
     acknowled
    -0.09
     consistent
    -0.09
     steward
    -0.09
    POSITIVE LOGITS
     compared
    0.14
     simulated
    0.13
     comparing
    0.13
     tested
    0.12
     Compared
    0.11
     reun
    0.10
     subsequently
    0.10
     hypothetical
    0.10
    tested
    0.10
     exposure
    0.09
    Activations Density 2.247%

    No Known Activations