© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29652
    Prev
    Next
    INDEX
    Explanations

    characters and plot elements

    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
     Pager
    -0.10
     confidence
    -0.10
     Confidence
    -0.10
     deposits
    -0.10
     needy
    -0.10
     someday
    -0.10
     deposit
    -0.10
     tutoring
    -0.09
     dormant
    -0.09
     hypoth
    -0.09
    POSITIVE LOGITS
     characters
    0.25
     storyline
    0.22
     scenes
    0.19
     plot
    0.19
     featuring
    0.19
     Characters
    0.19
     protagonists
    0.19
    characters
    0.18
     elements
    0.18
     realism
    0.18
    Activations Density 0.219%

    No Known Activations