© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111480
    Prev
    Next
    INDEX
    Explanations

    honestly, frankly, overall

    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
    Negative Logits
     XO
    -0.10
     hete
    -0.09
     objet
    -0.09
    etro
    -0.09
    ONSE
    -0.09
    /bus
    -0.08
    tod
    -0.08
    /Private
    -0.08
     Lod
    -0.08
    ATAL
    -0.08
    POSITIVE LOGITS
     overall
    0.11
     honestly
    0.11
     frankly
    0.11
    berger
    0.10
    —and
    0.10
     Storm
    0.10
    Overall
    0.10
     Ja
    0.10
     wax
    0.09
    dit
    0.09
    Activations Density 0.001%

    No Known Activations