© 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. 49074
    Prev
    Next
    INDEX
    Explanations

    revealing the truth

    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
    apel
    -0.10
    ipo
    -0.10
    umen
    -0.10
    atchet
    -0.10
    asu
    -0.09
     Armed
    -0.09
     presumably
    -0.09
    urement
    -0.09
    /by
    -0.09
    ackets
    -0.09
    POSITIVE LOGITS
     truth
    0.70
     Truth
    0.52
    truth
    0.49
    Truth
    0.48
     reality
    0.44
     truths
    0.38
     fact
    0.35
    _truth
    0.32
     truthful
    0.31
     Reality
    0.29
    Activations Density 0.164%

    No Known Activations