© 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. 27262
    Prev
    Next
    INDEX
    Explanations

    first, let's clarify or establish

    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
     subsequent
    -0.16
     subsequently
    -0.15
     eventually
    -0.15
     additionally
    -0.14
     afterward
    -0.13
     sooner
    -0.13
     ultimately
    -0.13
     further
    -0.13
     afterwards
    -0.13
     meanwhile
    -0.12
    POSITIVE LOGITS
     disclaimer
    0.15
     basics
    0.13
     establish
    0.12
    .Then
    0.11
     establishes
    0.10
    PB
    0.10
     familiar
    0.10
     general
    0.10
    pon
    0.10
     Basics
    0.10
    Activations Density 0.167%

    No Known Activations