© 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. 50439
    Prev
    Next
    INDEX
    Explanations

    problematic systemic issues

    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
     hopefully
    -0.14
     frowned
    -0.13
     Hopefully
    -0.12
     advoc
    -0.12
     envis
    -0.12
     slowdown
    -0.11
     bureaucr
    -0.11
     tapered
    -0.11
     somewhat
    -0.11
     boyc
    -0.11
    POSITIVE LOGITS
     profoundly
    0.14
     systematically
    0.13
     pervasive
    0.13
     systematic
    0.12
     urgently
    0.12
     fundamentally
    0.12
     structural
    0.12
     impover
    0.12
     fundamental
    0.11
     perv
    0.11
    Activations Density 0.972%

    No Known Activations