© 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. 5726
    Prev
    Next
    INDEX
    Explanations

    parts and features enhance system or object

    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
    ucch
    -0.12
    woods
    -0.11
    815
    -0.11
    wie
    -0.11
    ande
    -0.11
    handles
    -0.10
    uchs
    -0.10
    804
    -0.10
     identifiable
    -0.10
     weap
    -0.10
    POSITIVE LOGITS
     further
    0.24
     enhance
    0.18
     enhances
    0.17
     Enh
    0.17
     adds
    0.17
     enhancing
    0.16
     Further
    0.15
    enh
    0.14
    Further
    0.14
     height
    0.14
    Activations Density 0.297%

    No Known Activations