© 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. 4929
    Prev
    Next
    INDEX
    Explanations

    protagonist or character creation

    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
    Runtime
    -0.09
     interrupted
    -0.08
     miraculous
    -0.08
    quirer
    -0.08
    .direct
    -0.08
    ilters
    -0.08
    rase
    -0.08
    (newValue
    -0.08
    appers
    -0.08
     clips
    -0.08
    POSITIVE LOGITS
     character
    0.46
     characters
    0.41
     Character
    0.37
     Characters
    0.36
     characterization
    0.34
    character
    0.33
    Character
    0.33
    -character
    0.32
    Characters
    0.31
    characters
    0.31
    Activations Density 0.467%

    No Known Activations