© 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. 17296
    Prev
    Next
    INDEX
    Explanations

    security information on the internet

    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
     Sad
    -0.10
    Sad
    -0.09
    asp
    -0.09
    roker
    -0.09
     hab
    -0.09
    XL
    -0.09
     sadd
    -0.08
     irres
    -0.08
    atura
    -0.08
    .fm
    -0.08
    POSITIVE LOGITS
    .UUID
    0.09
    enario
    0.09
     Mull
    0.09
     Alias
    0.09
     Grand
    0.09
    eil
    0.09
    angel
    0.09
    alla
    0.09
    erus
    0.09
     Cent
    0.09
    Activations Density 0.001%

    No Known Activations