© 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. 89997
    Prev
    Next
    INDEX
    Explanations

    clutch, set, dress, outfit

    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
     quot
    -0.10
     Romero
    -0.10
     hus
    -0.09
     blankets
    -0.09
     Sofa
    -0.09
     hamm
    -0.08
    umo
    -0.08
    ÃĤ
    -0.08
     Pey
    -0.08
    uber
    -0.08
    POSITIVE LOGITS
     Shirley
    0.10
     CrossRef
    0.09
    /goto
    0.09
     outfit
    0.09
    /pub
    0.09
    ?action
    0.09
     Grim
    0.09
     basically
    0.09
    Enumeration
    0.09
     allegedly
    0.08
    Activations Density 0.023%

    No Known Activations