© 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. 50244
    Prev
    Next
    INDEX
    Explanations

    social media actions

    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
     spoken
    -0.13
     verbal
    -0.12
     Letter
    -0.12
     speeches
    -0.12
     letter
    -0.12
     spoke
    -0.11
     emails
    -0.11
     correspondence
    -0.11
     Emails
    -0.11
     orally
    -0.11
    POSITIVE LOGITS
     emoji
    0.20
     emojis
    0.19
     gif
    0.17
     GIF
    0.17
     emot
    0.16
     Emoji
    0.16
     gifs
    0.15
     links
    0.13
    emoji
    0.12
     capital
    0.12
    Activations Density 0.104%

    No Known Activations