© 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. 26451
    Prev
    Next
    INDEX
    Explanations

    favorite or choice

    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
    ame
    -0.11
    313
    -0.10
    987
    -0.10
     Cousins
    -0.09
    atz
    -0.09
    æī
    -0.09
    BTN
    -0.09
    MB
    -0.09
    113
    -0.09
    mel
    -0.09
    POSITIVE LOGITS
     choice
    0.16
    /pre
    0.16
    -choice
    0.13
     method
    0.12
     Choice
    0.12
     OPTION
    0.10
    /default
    0.10
    choice
    0.10
    Choice
    0.10
    entially
    0.10
    Activations Density 0.058%

    No Known Activations