© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15233
    Prev
    Next
    INDEX
    Explanations

    not a lie

    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
     sho
    -0.09
     sque
    -0.09
     anyway
    -0.09
     anyways
    -0.09
     Pes
    -0.08
     gol
    -0.08
     Sle
    -0.08
     shoe
    -0.08
     bother
    -0.08
     anyhow
    -0.08
    POSITIVE LOGITS
     caval
    0.13
     joking
    0.12
     kidding
    0.12
     flavors
    0.12
    uti
    0.12
    uts
    0.11
     whatsoever
    0.11
    afort
    0.11
    agen
    0.11
     hyper
    0.10
    Activations Density 0.015%

    No Known Activations