© 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. 91351
    Prev
    Next
    INDEX
    Explanations

    made a/the/sure/various

    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
    Hits
    -0.11
    lags
    -0.11
     upro
    -0.10
    hone
    -0.10
    ippo
    -0.10
    PDO
    -0.10
     afore
    -0.10
     exh
    -0.10
    Cou
    -0.10
     Acad
    -0.10
    POSITIVE LOGITS
     recommendations
    0.14
     payments
    0.13
     sure
    0.13
     preparations
    0.12
     observations
    0.11
     decisions
    0.11
     deposits
    0.11
     predictions
    0.11
     arrangements
    0.11
    sure
    0.11
    Activations Density 0.174%

    No Known Activations