© 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. 115218
    Prev
    Next
    INDEX
    Explanations

    **impersonate or 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
     deeply
    -0.10
     Gaines
    -0.09
     Guinness
    -0.09
    isc
    -0.09
    -vis
    -0.09
    SB
    -0.09
    upport
    -0.09
     Dra
    -0.08
    ija
    -0.08
     deposits
    -0.08
    POSITIVE LOGITS
    ality
    0.09
     Malik
    0.09
     playa
    0.09
     fors
    0.08
     availability
    0.08
    ãĥĥ
    0.08
     verm
    0.08
     mend
    0.08
    plementation
    0.08
     eminent
    0.08
    Activations Density 0.001%

    No Known Activations