© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115603
    Prev
    Next
    INDEX
    Explanations

    `: // or http://www followed by www

    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
     crispy
    -0.08
    UIL
    -0.08
    enton
    -0.07
     RPG
    -0.07
     autoload
    -0.07
    oble
    -0.07
     Dou
    -0.07
     resting
    -0.06
     pat
    -0.06
    ipl
    -0.06
    POSITIVE LOGITS
     dudes
    0.12
    trak
    0.11
     UNC
    0.11
     Kidd
    0.11
    orus
    0.11
     Arte
    0.11
     cigaret
    0.11
     Saud
    0.11
     downstream
    0.11
     Eigen
    0.10
    Activations Density 0.006%

    No Known Activations