© 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. 31043
    Prev
    Next
    INDEX
    Explanations

    comic book characters and publishers

    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
     fucked
    -0.10
     fuck
    -0.09
     DS
    -0.09
     JW
    -0.09
     Fuck
    -0.09
     fucking
    -0.09
    -picker
    -0.09
     Flake
    -0.09
     Fucked
    -0.09
     Novel
    -0.09
    POSITIVE LOGITS
     superhero
    0.40
     superheroes
    0.34
     Superman
    0.30
     Batman
    0.28
     Marvel
    0.28
     Gotham
    0.27
     Comics
    0.26
     comics
    0.25
    Batman
    0.24
     Avengers
    0.24
    Activations Density 0.401%

    No Known Activations