© 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. 32603
    Prev
    Next
    INDEX
    Explanations

    Copyright, author, programming

    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
     preceded
    -0.13
     Âł Âł
    -0.11
     unrealistic
    -0.11
     realistically
    -0.10
    burger
    -0.10
     Lets
    -0.10
     purported
    -0.10
     Whats
    -0.09
    aje
    -0.09
    Lets
    -0.09
    POSITIVE LOGITS
     Ec
    0.10
     '"
    0.10
     '
    0.10
     Nom
    0.08
     '(
    0.08
     Saint
    0.08
     lor
    0.08
    aviour
    0.08
     vinc
    0.08
    Ec
    0.08
    Activations Density 0.004%

    No Known Activations