© 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. 14748
    Prev
    Next
    INDEX
    Explanations

    paradise and utopian places

    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
    emen
    -0.09
    lett
    -0.08
    701
    -0.08
    ett
    -0.08
    CEF
    -0.08
     Warn
    -0.08
     sober
    -0.08
     marrow
    -0.08
     ance
    -0.08
     Rally
    -0.08
    POSITIVE LOGITS
     paradise
    0.14
     Paradise
    0.14
    -seeking
    0.11
     Nir
    0.11
     bliss
    0.11
     Bliss
    0.11
     island
    0.11
     resort
    0.11
     Eden
    0.11
     scape
    0.10
    Activations Density 0.035%

    No Known Activations