© 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. 89652
    Prev
    Next
    INDEX
    Explanations

    superheroes Wonder , Daredevil , X-Men , Spider-Man

    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
     Progressive
    -0.12
     progressive
    -0.09
    /models
    -0.09
     Johannes
    -0.09
    odka
    -0.09
     Moody
    -0.08
     Pok
    -0.08
     associates
    -0.08
     mill
    -0.08
    sek
    -0.08
    POSITIVE LOGITS
     Woman
    0.12
     Cond
    0.09
    etto
    0.09
    OutOf
    0.09
     sublic
    0.09
    aten
    0.09
    amer
    0.09
     Fist
    0.09
    evity
    0.09
    orra
    0.09
    Activations Density 0.030%

    No Known Activations