© 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. 26344
    Prev
    Next
    INDEX
    Explanations

    allow to enable

    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
     enrich
    -0.14
     enriched
    -0.13
    UGE
    -0.12
     Hass
    -0.12
     exacerb
    -0.12
    URT
    -0.12
     Rein
    -0.12
     scenic
    -0.12
    uge
    -0.11
    nga
    -0.11
    POSITIVE LOGITS
     allowing
    0.17
     enable
    0.17
     allow
    0.17
     enabling
    0.16
     sufficiently
    0.16
     overcome
    0.14
     permit
    0.14
     allows
    0.14
     enough
    0.14
     enables
    0.13
    Activations Density 0.553%

    No Known Activations