© 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. 111775
    Prev
    Next
    INDEX
    Explanations

    ignore or disregard

    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
    roi
    -0.13
     nearer
    -0.12
     identifiable
    -0.12
     prevented
    -0.12
     anywhere
    -0.12
     eliminated
    -0.11
    fw
    -0.11
     gast
    -0.11
    thouse
    -0.11
     BEFORE
    -0.11
    POSITIVE LOGITS
     altogether
    0.14
     bliss
    0.12
     completely
    0.12
     gaping
    0.11
     concentrated
    0.11
     entirely
    0.10
     focused
    0.10
     focus
    0.10
     impunity
    0.10
     focusing
    0.09
    Activations Density 0.057%

    No Known Activations