© 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. 32523
    Prev
    Next
    INDEX
    Explanations

    counting on or out

    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
     indem
    -0.10
    766
    -0.09
     Pang
    -0.09
    ILE
    -0.09
     tread
    -0.09
     cherry
    -0.09
     Doll
    -0.09
    arella
    -0.09
    utz
    -0.09
    ologia
    -0.09
    POSITIVE LOGITS
    enance
    0.16
     rely
    0.13
     relied
    0.13
     reliance
    0.12
     counted
    0.12
     expect
    0.11
    inue
    0.11
     expects
    0.10
     relies
    0.10
     depended
    0.10
    Activations Density 0.010%

    No Known Activations