© 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. 87983
    Prev
    Next
    INDEX
    Explanations

    that / que

    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
    #@
    -0.08
     pap
    -0.08
     cud
    -0.08
     Pap
    -0.07
    olas
    -0.07
     disponibles
    -0.07
    ãĤ
    -0.07
    #↵↵
    -0.07
    alue
    -0.07
    pes
    -0.07
    POSITIVE LOGITS
     crow
    0.12
     meanwhile
    0.12
     Somebody
    0.11
     Sans
    0.11
     besides
    0.10
    utto
    0.10
     characterize
    0.10
     Hoe
    0.10
    ioni
    0.10
     nowadays
    0.10
    Activations Density 0.168%

    No Known Activations