© 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. 115459
    Prev
    Next
    INDEX
    Explanations

    imagery and visualization

    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
     grooming
    -0.11
     pun
    -0.11
     groom
    -0.09
     Lust
    -0.09
     gio
    -0.09
    _interaction
    -0.09
     cons
    -0.09
     starred
    -0.09
    dee
    -0.08
     Dre
    -0.08
    POSITIVE LOGITS
     visualization
    0.42
     imagining
    0.41
     visualize
    0.38
     imagination
    0.38
     envision
    0.37
     imag
    0.37
     imagined
    0.37
     Visualization
    0.35
     imagery
    0.34
     imagine
    0.34
    Activations Density 0.187%

    No Known Activations