© 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. 46687
    Prev
    Next
    INDEX
    Explanations

    natural progression or consequence

    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
    itto
    -0.10
     Mond
    -0.10
     Zam
    -0.10
     ENG
    -0.10
    enko
    -0.09
     whence
    -0.09
    AU
    -0.09
    roy
    -0.09
     indefinitely
    -0.09
     strange
    -0.09
    POSITIVE LOGITS
     progression
    0.21
     natural
    0.21
     naturally
    0.16
     inclination
    0.15
     tendency
    0.15
    natural
    0.15
    Natural
    0.15
     Natural
    0.14
     outward
    0.14
     logical
    0.14
    Activations Density 0.023%

    No Known Activations