© 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. 14840
    Prev
    Next
    INDEX
    Explanations

    names ending with specific suffixes

    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
     gag
    -0.09
     hans
    -0.09
     pup
    -0.08
     Barcl
    -0.08
     intervening
    -0.08
     Bott
    -0.08
    otec
    -0.08
     hamm
    -0.08
    script
    -0.08
     homemade
    -0.08
    POSITIVE LOGITS
     LJ
    0.27
     lj
    0.21
    .live
    0.21
    (no
    0.19
     journal
    0.19
    lj
    0.19
     userinfo
    0.17
    userinfo
    0.17
     journals
    0.16
     Live
    0.16
    Activations Density 0.159%

    No Known Activations