© 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. 91255
    Prev
    Next
    INDEX
    Explanations

    said Thursday, people Austin

    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
     Jad
    -0.09
     (('
    -0.09
     transient
    -0.09
    @dynamic
    -0.09
     trunk
    -0.09
    fos
    -0.09
     imposition
    -0.09
     '
    -0.08
     draped
    -0.08
     provisioning
    -0.08
    POSITIVE LOGITS
     HuffPost
    0.15
     BuzzFeed
    0.12
     Huffington
    0.11
     Quiz
    0.10
    Buzz
    0.09
     spun
    0.09
     Beng
    0.09
     Flour
    0.09
    usband
    0.09
     Buzz
    0.09
    Activations Density 0.057%

    No Known Activations