© 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. 5894
    Prev
    Next
    INDEX
    Explanations

    roles and professions

    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
    ela
    -0.10
    egin
    -0.09
     pa
    -0.09
     Bair
    -0.09
    vens
    -0.09
     Bain
    -0.08
     cuz
    -0.08
    imar
    -0.08
     clap
    -0.08
     PA
    -0.08
    POSITIVE LOGITS
     myself
    0.22
     yourself
    0.14
    oby
    0.12
    chia
    0.11
    iou
    0.11
     naturally
    0.10
     ourselves
    0.10
    ,I
    0.10
     alone
    0.10
     constantly
    0.10
    Activations Density 0.075%

    No Known Activations