© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113663
    Prev
    Next
    INDEX
    Explanations

    truth and reality distortion

    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
     attracting
    -0.12
    Inactive
    -0.12
     shy
    -0.11
     stereotype
    -0.11
     inactive
    -0.11
    anten
    -0.11
     Ster
    -0.10
     inherits
    -0.10
    quota
    -0.10
     laz
    -0.10
    POSITIVE LOGITS
     Orwell
    0.23
     reality
    0.22
     Reality
    0.19
     distortion
    0.19
     distort
    0.19
     sanity
    0.18
     truth
    0.17
     Sanity
    0.17
     distorted
    0.17
     propaganda
    0.16
    Activations Density 0.194%

    No Known Activations