© 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. 89752
    Prev
    Next
    INDEX
    Explanations

    Star Wars and science fiction

    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
     unt
    -0.10
     Atl
    -0.08
     explosive
    -0.08
     Gotham
    -0.08
    ilet
    -0.08
     deton
    -0.08
     Hog
    -0.08
     Hok
    -0.08
     practice
    -0.08
     Fors
    -0.07
    POSITIVE LOGITS
     Jab
    0.12
     Hayden
    0.12
     Ob
    0.11
     Malta
    0.11
    Ob
    0.11
     Dy
    0.11
     wan
    0.10
     dy
    0.10
     Skywalker
    0.10
    iche
    0.10
    Activations Density 0.123%

    No Known Activations