© 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. 112535
    Prev
    Next
    INDEX
    Explanations

    software names and projects

    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
    's
    -0.14
    ’s
    -0.13
     itself
    -0.10
     reel
    -0.09
     Largest
    -0.09
     deadliest
    -0.08
    538
    -0.08
    amac
    -0.08
    ampire
    -0.08
    aki
    -0.08
    POSITIVE LOGITS
    /C
    0.10
     Garn
    0.09
    /P
    0.09
    -induced
    0.09
    ican
    0.09
    /Dk
    0.09
    -created
    0.09
     brand
    0.09
    /O
    0.08
     Giov
    0.08
    Activations Density 1.020%

    No Known Activations