© 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. 49934
    Prev
    Next
    INDEX
    Explanations

    secret communication

    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
     gaz
    -0.10
     foreseeable
    -0.10
     regenerated
    -0.10
     dormant
    -0.10
     unins
    -0.10
     stagnant
    -0.10
     Gazette
    -0.10
     hosp
    -0.10
    vars
    -0.09
    inters
    -0.09
    POSITIVE LOGITS
     whisper
    0.41
     discreet
    0.40
     whispered
    0.39
     secrecy
    0.38
     confidential
    0.37
     secretive
    0.37
     clandest
    0.34
     whispers
    0.34
     covert
    0.34
     stealth
    0.33
    Activations Density 0.025%

    No Known Activations