© 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. 90391
    Prev
    Next
    INDEX
    Explanations

    how something works well

    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
     proper
    -0.08
    Duplicate
    -0.07
     unint
    -0.07
     orderly
    -0.07
     meaningful
    -0.07
     NotImplemented
    -0.07
     Said
    -0.07
    inan
    -0.07
     clas
    -0.06
     Valerie
    -0.06
    POSITIVE LOGITS
     best
    0.17
     fine
    0.16
     wonders
    0.16
     great
    0.16
     differently
    0.15
     similarly
    0.15
     similar
    0.15
    FINE
    0.14
     surprisingly
    0.14
     Fine
    0.14
    Activations Density 0.065%

    No Known Activations