© 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. 26450
    Prev
    Next
    INDEX
    Explanations

    pricked up, attention caught, interested

    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
     fug
    -0.09
     thanked
    -0.09
    alion
    -0.09
     thanking
    -0.09
     McMahon
    -0.09
     resolution
    -0.08
    idot
    -0.08
     torrents
    -0.08
     rond
    -0.08
     satisfaction
    -0.08
    POSITIVE LOGITS
     intrigued
    0.49
     intrigue
    0.43
     intriguing
    0.39
     curiosity
    0.39
     interest
    0.38
     intrig
    0.38
     Intr
    0.36
     Interest
    0.34
     curious
    0.31
     interested
    0.31
    Activations Density 0.120%

    No Known Activations