© 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. 48529
    Prev
    Next
    INDEX
    Explanations

    mistaken for, mimic, fooled

    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
     Visible
    -0.12
     visible
    -0.12
    Visible
    -0.10
     bac
    -0.09
    visible
    -0.09
    -visible
    -0.09
    bubble
    -0.09
     disgust
    -0.09
     suction
    -0.09
     characteristic
    -0.09
    POSITIVE LOGITS
     mistaken
    0.23
     confuse
    0.14
     mistake
    0.14
     confused
    0.14
     confusion
    0.13
     convinc
    0.13
     passes
    0.12
     pass
    0.11
     overlooked
    0.11
     ambiguous
    0.11
    Activations Density 0.034%

    No Known Activations