© 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. 28060
    Prev
    Next
    INDEX
    Explanations

    reading an article or text conditions

    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
     readings
    -0.10
     documentary
    -0.09
     videos
    -0.09
    rete
    -0.09
     video
    -0.08
     communic
    -0.08
     Overse
    -0.08
     documentaries
    -0.08
     Videos
    -0.08
     verbally
    -0.08
    POSITIVE LOGITS
     aloud
    0.34
     attent
    0.19
    /watch
    0.17
     carefully
    0.15
     thoroughly
    0.14
    /list
    0.13
     lips
    0.12
    loud
    0.12
    /write
    0.11
    ily
    0.11
    Activations Density 0.252%

    No Known Activations