© 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. 28803
    Prev
    Next
    INDEX
    Explanations

    imagining or envisioning future events

    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
     blame
    -0.11
     blames
    -0.11
    witch
    -0.10
    KY
    -0.10
     miscon
    -0.10
    rect
    -0.10
    lla
    -0.10
     blaming
    -0.10
    riv
    -0.09
     Parr
    -0.09
    POSITIVE LOGITS
     envision
    0.24
     visualization
    0.22
     Visualization
    0.21
     visualize
    0.21
     envisioned
    0.21
     vivid
    0.20
     envis
    0.19
     vision
    0.19
     Vision
    0.19
    vision
    0.18
    Activations Density 0.071%

    No Known Activations