© 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. 88212
    Prev
    Next
    INDEX
    Explanations

    when proposing or suggesting

    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
     cogn
    -0.10
     Wilde
    -0.09
    ĵį
    -0.09
     Antworten
    -0.08
    odium
    -0.08
     hype
    -0.08
    ë§
    -0.08
    heit
    -0.08
    unday
    -0.08
    cac
    -0.08
    POSITIVE LOGITS
     announce
    0.30
     announcement
    0.30
     suggestion
    0.27
     announcing
    0.27
     announced
    0.27
     mention
    0.27
     proposal
    0.27
     announces
    0.26
     propose
    0.25
     mentioning
    0.25
    Activations Density 0.104%

    No Known Activations