© 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. 33029
    Prev
    Next
    INDEX
    Explanations

    honestly, frankly, truth

    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
    liner
    -0.10
     Fot
    -0.10
     Seam
    -0.09
    inton
    -0.09
    alar
    -0.09
     conting
    -0.08
    AZY
    -0.08
     Fritz
    -0.08
    129
    -0.08
     root
    -0.08
    POSITIVE LOGITS
     honestly
    0.74
     frankly
    0.68
     Honestly
    0.54
     tb
    0.51
    Honestly
    0.48
     truth
    0.43
     admittedly
    0.38
     honest
    0.38
     TB
    0.36
     Truth
    0.33
    Activations Density 0.249%

    No Known Activations