© 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. 4057
    Prev
    Next
    INDEX
    Explanations

    bond strength, bonding systems, bond lengths

    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
     Hamp
    -0.09
    olson
    -0.09
    ened
    -0.09
    erals
    -0.09
    LAS
    -0.09
     Sext
    -0.09
     oversh
    -0.08
     ec
    -0.08
     shed
    -0.08
    ument
    -0.08
    POSITIVE LOGITS
     Bond
    0.22
     bonding
    0.20
     bond
    0.19
    bond
    0.17
    Bond
    0.17
     bonded
    0.17
     bonds
    0.16
    /bind
    0.15
     bondage
    0.15
     Bonds
    0.12
    Activations Density 0.013%

    No Known Activations