© 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. 8037
    Prev
    Next
    INDEX
    Explanations

    official positions and outcomes

    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
     lately
    -0.13
    è¿ij
    -0.12
    efa
    -0.11
     unsuccessfully
    -0.11
     differently
    -0.10
     repeatedly
    -0.10
     elsewhere
    -0.10
    illo
    -0.10
    afa
    -0.10
    ulum
    -0.09
    POSITIVE LOGITS
     officially
    0.21
     unanimously
    0.20
     outright
    0.17
     indefinite
    0.17
     permanently
    0.16
     indefinitely
    0.16
     formally
    0.15
     pending
    0.15
     instantly
    0.14
     prelim
    0.14
    Activations Density 0.788%

    No Known Activations