© 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. 7519
    Prev
    Next
    INDEX
    Explanations

    never activated or happened

    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
     Sor
    -0.09
     Dexter
    -0.08
     Batt
    -0.08
     prefect
    -0.08
    amb
    -0.08
     Spare
    -0.08
     pressured
    -0.08
     Kathleen
    -0.08
    amas
    -0.08
     Bart
    -0.08
    POSITIVE LOGITS
     actually
    0.23
     actual
    0.19
    actually
    0.18
     Actually
    0.18
    Actually
    0.14
    actual
    0.14
     Actual
    0.14
     actu
    0.13
    Actual
    0.12
    (actual
    0.12
    Activations Density 0.146%

    No Known Activations