© 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. 117059
    Prev
    Next
    INDEX
    Explanations

    delusion, illusion, mistaken belief

    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
     Critics
    -0.13
     criticisms
    -0.13
     sarc
    -0.12
    Crit
    -0.12
     criticism
    -0.12
     Crit
    -0.12
     impatient
    -0.11
     critics
    -0.11
     sarcast
    -0.11
     mockery
    -0.10
    POSITIVE LOGITS
     del
    0.38
     belief
    0.38
     believing
    0.37
     misconception
    0.36
     illusions
    0.34
     mistaken
    0.33
     miscon
    0.33
     illusion
    0.32
     believes
    0.30
     misguided
    0.30
    Activations Density 0.376%

    No Known Activations