© 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. 114002
    Prev
    Next
    INDEX
    Explanations

    has/have/will be/been

    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
    ulia
    -0.14
    beck
    -0.13
     #'
    -0.13
    unan
    -0.13
    flu
    -0.13
    Escort
    -0.13
    \\\
    -0.13
    793
    -0.13
    ioso
    -0.13
    asca
    -0.13
    POSITIVE LOGITS
     be
    0.09
     exist
    0.07
     arise
    0.06
     seated
    0.06
     bog
    0.06
     Vest
    0.06
     pil
    0.05
     bem
    0.05
     fet
    0.05
     cr
    0.05
    Activations Density 0.041%

    No Known Activations