© 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. 28828
    Prev
    Next
    INDEX
    Explanations

    decrypting passwords

    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
     covert
    -0.12
    erna
    -0.12
     myriad
    -0.10
     passionately
    -0.10
     (![
    -0.10
     Serena
    -0.10
     divul
    -0.09
    �t
    -0.09
     countless
    -0.09
     dazzling
    -0.09
    POSITIVE LOGITS
     Jah
    0.11
     federation
    0.09
     Distrib
    0.09
     grosse
    0.09
     fart
    0.09
     Dien
    0.09
     Coleman
    0.08
     camps
    0.08
     gross
    0.08
     raped
    0.08
    Activations Density 0.013%

    No Known Activations