© 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. 114266
    Prev
    Next
    INDEX
    Explanations

    imitation and impersonation

    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
     Sabb
    -0.09
    );\
    -0.09
     Hayward
    -0.09
     pam
    -0.09
     Bris
    -0.09
     appealed
    -0.09
     Riot
    -0.08
     symb
    -0.08
    heim
    -0.08
     enfrent
    -0.08
    POSITIVE LOGITS
     imitation
    0.43
     imperson
    0.36
     mimic
    0.33
     mim
    0.30
     impression
    0.28
     impressions
    0.25
    imit
    0.24
     Mim
    0.24
     emulate
    0.23
     im
    0.22
    Activations Density 0.081%

    No Known Activations