© 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. 31221
    Prev
    Next
    INDEX
    Explanations

    -ologists

    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
     portions
    -0.10
     looks
    -0.10
     capabilities
    -0.09
     freedoms
    -0.09
     Cheers
    -0.09
     trop
    -0.09
    822
    -0.09
     pieces
    -0.09
     Portions
    -0.09
    구
    -0.09
    POSITIVE LOGITS
    ologists
    0.14
    rians
    0.13
    acists
    0.11
    ians
    0.11
    archs
    0.11
    icans
    0.10
    sters
    0.10
    ists
    0.10
    gars
    0.09
    ocrats
    0.09
    Activations Density 0.416%

    No Known Activations