© 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. 16853
    Prev
    Next
    INDEX
    Explanations

    desire or desires

    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
    agers
    -0.11
     disguise
    -0.10
    age
    -0.10
    ings
    -0.10
    tober
    -0.10
    itude
    -0.10
    sville
    -0.09
    iness
    -0.09
    icity
    -0.09
    ique
    -0.09
    POSITIVE LOGITS
    ably
    0.13
    ment
    0.10
    oso
    0.10
    osos
    0.10
    ments
    0.10
    orption
    0.09
    ptive
    0.09
    ous
    0.09
    bable
    0.09
    angu
    0.09
    Activations Density 0.105%

    No Known Activations