© 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. 17896
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

    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
     contempor
    -0.08
    /E
    -0.07
     -:
    -0.07
    /Y
    -0.07
     ((
    -0.07
    ekte
    -0.07
    ottes
    -0.07
    ï¼ı
    -0.07
     Wax
    -0.07
    POSITIVE LOGITS
     mess
    0.12
     Ged
    0.11
    ...");č↵
    0.11
     Tod
    0.10
    inent
    0.10
     viz
    0.10
    PCI
    0.10
     Dort
    0.10
    âĢ¦)
    0.10
     Morris
    0.10
    Activations Density 0.002%

    No Known Activations