© 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. 48136
    Prev
    Next
    INDEX
    Explanations

    would make

    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
     Britt
    -0.10
    -bordered
    -0.10
     Bren
    -0.10
    itational
    -0.09
     dint
    -0.09
    oyer
    -0.09
     Reeves
    -0.09
    ,ep
    -0.09
     compuls
    -0.09
     hust
    -0.09
    POSITIVE LOGITS
     forever
    0.21
     someday
    0.17
     sooner
    0.17
     gladly
    0.14
     permanently
    0.14
     soon
    0.13
     later
    0.13
     everlasting
    0.13
     if
    0.13
     permanent
    0.13
    Activations Density 0.004%

    No Known Activations