© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31889
    Prev
    Next
    INDEX
    Explanations

    DOM manipulation and updates

    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
     commande
    -0.11
     mysterious
    -0.10
     elusive
    -0.10
     purpos
    -0.09
     captivity
    -0.09
    awan
    -0.09
     hij
    -0.09
     directions
    -0.09
     liner
    -0.09
    /accounts
    -0.09
    POSITIVE LOGITS
     blinked
    0.15
     standing
    0.14
     blink
    0.13
     blinking
    0.12
     attire
    0.12
     instantly
    0.12
     appeared
    0.11
     stood
    0.11
     Blink
    0.11
     clothes
    0.10
    Activations Density 0.065%

    No Known Activations