© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    supposed to feel or believe

    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
    uin
    -0.12
     undis
    -0.11
    airo
    -0.10
    BB
    -0.10
    ikal
    -0.10
     Catal
    -0.10
     Pou
    -0.10
    kos
    -0.10
     Laf
    -0.10
     stat
    -0.10
    POSITIVE LOGITS
     ashamed
    0.13
     lest
    0.12
     SHOULD
    0.12
     shameful
    0.12
     discouraged
    0.12
     distrust
    0.11
     beware
    0.11
     discour
    0.11
     Bew
    0.11
     supposedly
    0.10
    Activations Density 0.063%

    No Known Activations