© 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. 30449
    Prev
    Next
    INDEX
    Explanations

    imagined scenarios and worlds

    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
     arts
    -0.10
     artwork
    -0.09
     Arts
    -0.09
     sculpture
    -0.09
     Genuine
    -0.09
     consec
    -0.09
     art
    -0.09
     essentials
    -0.08
     legitimately
    -0.08
     decoration
    -0.08
    POSITIVE LOGITS
     scenarios
    0.24
     fantast
    0.20
     scenario
    0.18
     unrealistic
    0.18
     hypothetical
    0.18
     imagined
    0.17
     imaginary
    0.17
     unlikely
    0.17
     fantasy
    0.16
     unreal
    0.16
    Activations Density 0.054%

    No Known Activations