© 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. 116494
    Prev
    Next
    INDEX
    Explanations

    you can create

    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
     assist
    -0.10
     acqu
    -0.09
    gy
    -0.09
     Beard
    -0.08
    HELP
    -0.08
     recur
    -0.08
     HELP
    -0.08
    /help
    -0.08
     nic
    -0.08
     sond
    -0.08
    POSITIVE LOGITS
     enjoy
    0.18
     customize
    0.17
     choose
    0.16
     chose
    0.16
    享
    0.15
     tailor
    0.14
     Enjoy
    0.14
     enjoying
    0.14
     experiencing
    0.14
     enjoys
    0.13
    Activations Density 0.049%

    No Known Activations