© 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. 115120
    Prev
    Next
    INDEX
    Explanations

    deception or being 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
    asy
    -0.11
     asn
    -0.10
    ulta
    -0.10
     capable
    -0.09
     Bain
    -0.09
     pedestal
    -0.09
    /ns
    -0.09
     bast
    -0.09
     Aus
    -0.09
     Wish
    -0.08
    POSITIVE LOGITS
     treats
    0.14
     treat
    0.13
     fooled
    0.13
     confused
    0.12
     emergencies
    0.11
     trick
    0.11
     simulate
    0.11
     simulated
    0.11
     confuse
    0.11
     false
    0.10
    Activations Density 0.134%

    No Known Activations