© 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. 88254
    Prev
    Next
    INDEX
    Explanations

    imaginary or fantastical 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
     etiquette
    -0.10
     spotlight
    -0.09
    inton
    -0.09
     obed
    -0.09
     sexist
    -0.09
     Amateur
    -0.08
     insensitive
    -0.08
     contempt
    -0.08
     strut
    -0.08
     observational
    -0.08
    POSITIVE LOGITS
     fantasy
    0.44
     fantast
    0.40
     Fantasy
    0.38
     mythical
    0.35
     magical
    0.35
     mystical
    0.34
     supernatural
    0.33
     fairy
    0.32
     fantasies
    0.32
    Fant
    0.31
    Activations Density 0.220%

    No Known Activations