© 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. 116469
    Prev
    Next
    INDEX
    Explanations

    seeing or noticing something

    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
    ervo
    -0.12
     interp
    -0.11
     scraper
    -0.10
     Femme
    -0.10
    #w
    -0.10
     emulator
    -0.10
     gonna
    -0.10
    æĶ
    -0.10
     Mono
    -0.10
     Gret
    -0.10
    POSITIVE LOGITS
     visible
    0.12
     see
    0.12
     her
    0.11
     seeing
    0.11
     saw
    0.11
     glimps
    0.11
     visibly
    0.10
     visibility
    0.10
     him
    0.10
     sees
    0.10
    Activations Density 0.002%

    No Known Activations