© 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. 17144
    Prev
    Next
    INDEX
    Explanations

    labeling and classification

    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
     overt
    -0.10
     auditor
    -0.10
     shores
    -0.09
     Fitz
    -0.09
     Fitzgerald
    -0.09
     backstage
    -0.09
     odds
    -0.09
     eyes
    -0.09
     ahead
    -0.09
    ajo
    -0.09
    POSITIVE LOGITS
    omat
    0.12
    achi
    0.10
    swith
    0.09
     intertwined
    0.09
    -highlight
    0.09
    enh
    0.09
     couch
    0.09
    ivism
    0.08
    eor
    0.08
     sofa
    0.08
    Activations Density 0.011%

    No Known Activations