© 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. 28376
    Prev
    Next
    INDEX
    Explanations

    dis- prefix

    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
     nons
    -0.10
     bitterly
    -0.09
    pent
    -0.09
     prim
    -0.09
    ells
    -0.08
     devis
    -0.08
     abl
    -0.08
     bitter
    -0.08
     masc
    -0.08
    kov
    -0.08
    POSITIVE LOGITS
    /dis
    0.14
     dis
    0.14
    (dis
    0.12
    -dis
    0.12
    .dis
    0.12
    DIS
    0.11
    dis
    0.11
    enuous
    0.11
     disemb
    0.11
    Dis
    0.11
    Activations Density 0.156%

    No Known Activations