© 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. 111399
    Prev
    Next
    INDEX
    Explanations

    journal citations and publication details

    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
     oppos
    -0.12
     chapters
    -0.11
    HR
    -0.10
     deselect
    -0.10
     Signal
    -0.09
     pulse
    -0.09
    /pass
    -0.09
    zb
    -0.09
    dal
    -0.09
     Lesb
    -0.09
    POSITIVE LOGITS
     received
    0.09
    Received
    0.09
     experienced
    0.09
    annon
    0.09
     j
    0.08
     Received
    0.08
    ondo
    0.08
     conquered
    0.08
     proced
    0.08
    received
    0.08
    Activations Density 0.352%

    No Known Activations