© 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. 114303
    Prev
    Next
    INDEX
    Explanations

    lies and mistruths

    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
     premiere
    -0.09
     incontro
    -0.09
     masters
    -0.09
     reputed
    -0.08
     lips
    -0.08
     lungs
    -0.08
    /bus
    -0.08
    ãĤī
    -0.08
     liberty
    -0.08
     stature
    -0.08
    POSITIVE LOGITS
     outright
    0.17
     jokes
    0.17
     illusions
    0.14
     satire
    0.14
     gossip
    0.13
     indirect
    0.13
     situ
    0.12
     trivia
    0.12
     direct
    0.12
     misunderstand
    0.12
    Activations Density 0.204%

    No Known Activations