© 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. 116500
    Prev
    Next
    INDEX
    Explanations

    security, protocols, encryption

    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
     zipper
    -0.09
     Maduro
    -0.08
    aped
    -0.08
     Winston
    -0.08
     Salv
    -0.08
    imei
    -0.08
     IllegalAccessException
    -0.08
     kir
    -0.08
    /cloud
    -0.08
     ceremon
    -0.08
    POSITIVE LOGITS
     decryption
    0.11
    mun
    0.10
     recurs
    0.09
     PK
    0.09
    defer
    0.09
     Banc
    0.09
     Marion
    0.08
    uzu
    0.08
    äng
    0.08
     Privacy
    0.08
    Activations Density 0.069%

    No Known Activations