© 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. 14038
    Prev
    Next
    INDEX
    Explanations

    disclaimer

    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
    esser
    -0.12
     crim
    -0.11
     slack
    -0.11
    inkel
    -0.11
    gratis
    -0.11
    rew
    -0.11
     succ
    -0.11
     negligent
    -0.11
     poll
    -0.11
     Rath
    -0.11
    POSITIVE LOGITS
    以ä¸Ĭ
    0.09
     beep
    0.07
    This
    0.07
     adv
    0.07
    ADV
    0.07
     This
    0.06
    æľ¬
    0.06
    .."
    0.06
     Maritime
    0.06
    olini
    0.06
    Activations Density 0.030%

    No Known Activations